Version Description
- Info: This plugin is way more work than expected, please motivate me by giving it a good review and also my trying my other plugins (https://meowapps.com). Thanks a lot for that :) I will do my best to make this plugin perfect.
- Update: Avoid interfering at all with all Ajax/Rest requests.
- Update: Use HtmlDomParser instead of DiDom (this parser is less sensitive to badly formatted HTML). I am also thinking of doing it all with regexp, but let's see that later.
- Info: Sorry for the last bunch of updates, some way of modifying HTML works for some, and not for others, and I am still trying to find a solution which works for everyone.
Download this release
Release Info
Developer | TigrouMeow |
Plugin | Gallery Custom Links |
Version | 1.0.9 |
Comparing to | |
See all releases |
Code changes from version 1.0.8 to 1.0.9
- composer.json +2 -1
- composer.lock +47 -1
- gallery_custom_links.php +2 -2
- mgcl_core.php +54 -35
- readme.txt +9 -3
- vendor/composer/autoload_namespaces.php +1 -0
- vendor/composer/autoload_static.php +11 -0
- vendor/composer/installed.json +48 -0
- vendor/kub-at/php-simple-html-dom-parser/CONTRIBUTING.md +3 -0
- vendor/kub-at/php-simple-html-dom-parser/LICENSE +21 -0
- vendor/kub-at/php-simple-html-dom-parser/README.md +29 -0
- vendor/kub-at/php-simple-html-dom-parser/composer.json +24 -0
- vendor/kub-at/php-simple-html-dom-parser/src/KubAT/PhpSimple/HtmlDomParser.php +16 -0
- vendor/kub-at/php-simple-html-dom-parser/src/KubAT/PhpSimple/lib/simple_html_dom.php +2174 -0
composer.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"require": {
|
3 |
-
"imangazaliev/didom": "^1.14"
|
|
|
4 |
}
|
5 |
}
|
1 |
{
|
2 |
"require": {
|
3 |
+
"imangazaliev/didom": "^1.14",
|
4 |
+
"kub-at/php-simple-html-dom-parser": "^1.7"
|
5 |
}
|
6 |
}
|
composer.lock
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
|
5 |
"This file is @generated automatically"
|
6 |
],
|
7 |
-
"content-hash": "
|
8 |
"packages": [
|
9 |
{
|
10 |
"name": "imangazaliev/didom",
|
@@ -54,6 +54,52 @@
|
|
54 |
"xml"
|
55 |
],
|
56 |
"time": "2019-01-17T11:01:36+00:00"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"packages-dev": [],
|
4 |
"Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
|
5 |
"This file is @generated automatically"
|
6 |
],
|
7 |
+
"content-hash": "580c75a9e32770a65f6b4d397a87b25d",
|
8 |
"packages": [
|
9 |
{
|
10 |
"name": "imangazaliev/didom",
|
54 |
"xml"
|
55 |
],
|
56 |
"time": "2019-01-17T11:01:36+00:00"
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"name": "kub-at/php-simple-html-dom-parser",
|
60 |
+
"version": "1.7.1",
|
61 |
+
"source": {
|
62 |
+
"type": "git",
|
63 |
+
"url": "https://github.com/Kub-AT/php-simple-html-dom-parser.git",
|
64 |
+
"reference": "7a745b20157efb0f1be3021394769bd6b8e9ed4e"
|
65 |
+
},
|
66 |
+
"dist": {
|
67 |
+
"type": "zip",
|
68 |
+
"url": "https://api.github.com/repos/Kub-AT/php-simple-html-dom-parser/zipball/7a745b20157efb0f1be3021394769bd6b8e9ed4e",
|
69 |
+
"reference": "7a745b20157efb0f1be3021394769bd6b8e9ed4e",
|
70 |
+
"shasum": ""
|
71 |
+
},
|
72 |
+
"require": {
|
73 |
+
"php": ">=5.3.2"
|
74 |
+
},
|
75 |
+
"type": "library",
|
76 |
+
"autoload": {
|
77 |
+
"psr-0": {
|
78 |
+
"KubAT\\PhpSimple\\HtmlDomParser": "src/"
|
79 |
+
}
|
80 |
+
},
|
81 |
+
"notification-url": "https://packagist.org/downloads/",
|
82 |
+
"license": [
|
83 |
+
"MIT"
|
84 |
+
],
|
85 |
+
"authors": [
|
86 |
+
{
|
87 |
+
"name": "S.C. Chen",
|
88 |
+
"email": "me578022@gmail.com"
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"name": "Jakub Stawowy",
|
92 |
+
"email": "Kub-AT@users.noreply.github.com"
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"description": "PHP Simple HTML DOM Parser with namespace and PHP 7.3 compatible",
|
96 |
+
"homepage": "http://simplehtmldom.sourceforge.net/",
|
97 |
+
"keywords": [
|
98 |
+
"Simple",
|
99 |
+
"dom",
|
100 |
+
"html"
|
101 |
+
],
|
102 |
+
"time": "2019-01-02T14:33:28+00:00"
|
103 |
}
|
104 |
],
|
105 |
"packages-dev": [],
|
gallery_custom_links.php
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
Plugin Name: Gallery Custom Links
|
4 |
Plugin URI: https://meowapps.com
|
5 |
Description: Gallery Custom Links allows you to link images from galleries to a specified URL. Tested with WordPress Gallery, Gutenberg, the Meow Gallery and others.
|
6 |
-
Version: 1.0.
|
7 |
Author: Jordy Meow
|
8 |
Author URI: https://meowapps.com
|
9 |
Text Domain: gallery-custom-links
|
@@ -23,7 +23,7 @@ if ( class_exists( 'Meow_Gallery_Custom_Links' ) ) {
|
|
23 |
}
|
24 |
|
25 |
global $mgcl_version;
|
26 |
-
$mgcl_version = '1.0.
|
27 |
|
28 |
include "mgcl_admin.php";
|
29 |
$mgcl_admin = new Meow_Gallery_Custom_Links_Admin( 'mgcl', __FILE__, 'gallery-custom-links' );
|
3 |
Plugin Name: Gallery Custom Links
|
4 |
Plugin URI: https://meowapps.com
|
5 |
Description: Gallery Custom Links allows you to link images from galleries to a specified URL. Tested with WordPress Gallery, Gutenberg, the Meow Gallery and others.
|
6 |
+
Version: 1.0.9
|
7 |
Author: Jordy Meow
|
8 |
Author URI: https://meowapps.com
|
9 |
Text Domain: gallery-custom-links
|
23 |
}
|
24 |
|
25 |
global $mgcl_version;
|
26 |
+
$mgcl_version = '1.0.9';
|
27 |
|
28 |
include "mgcl_admin.php";
|
29 |
$mgcl_admin = new Meow_Gallery_Custom_Links_Admin( 'mgcl', __FILE__, 'gallery-custom-links' );
|
mgcl_core.php
CHANGED
@@ -4,18 +4,23 @@ require_once 'vendor/autoload.php';
|
|
4 |
|
5 |
use DiDom\Document;
|
6 |
use DiDom\Element;
|
|
|
7 |
|
8 |
class Meow_Gallery_Custom_Links
|
9 |
{
|
10 |
public $isEnabled = true;
|
11 |
-
|
|
|
|
|
|
|
12 |
|
13 |
public function __construct() {
|
14 |
|
15 |
-
if ( is_admin() )
|
16 |
return;
|
|
|
17 |
|
18 |
-
if ( $this->
|
19 |
add_action( 'init', array( $this, 'start' ) );
|
20 |
add_action( 'shutdown', array( $this, 'shutdown' ) );
|
21 |
add_action( 'wp_footer', array( $this, 'unlink_lightboxes_script' ) ) ;
|
@@ -26,6 +31,24 @@ class Meow_Gallery_Custom_Links
|
|
26 |
}
|
27 |
}
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
function init() {
|
30 |
//add_action( 'init', array( $this, 'init' ) );
|
31 |
// We don't need this now, we go through all the images.
|
@@ -35,7 +58,7 @@ class Meow_Gallery_Custom_Links
|
|
35 |
|
36 |
function start() {
|
37 |
$this->isEnabled = apply_filters( 'gallery_custom_links_enabled', true );
|
38 |
-
if ( $this->isEnabled && $this->
|
39 |
ob_start( array( $this, "linkify" ) );
|
40 |
}
|
41 |
|
@@ -82,40 +105,36 @@ class Meow_Gallery_Custom_Links
|
|
82 |
if ( empty( $target ) )
|
83 |
$target = '_self';
|
84 |
$parent = $element->parent();
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
}
|
99 |
-
|
100 |
-
$potentialLinkNode = $potentialLinkNode->parent();
|
101 |
-
else
|
102 |
-
break;
|
103 |
}
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
$
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
$
|
117 |
}
|
118 |
-
$parent->appendChild( $a );
|
119 |
return true;
|
120 |
}
|
121 |
}
|
4 |
|
5 |
use DiDom\Document;
|
6 |
use DiDom\Element;
|
7 |
+
use KubAT\PhpSimple\HtmlDomParser;
|
8 |
|
9 |
class Meow_Gallery_Custom_Links
|
10 |
{
|
11 |
public $isEnabled = true;
|
12 |
+
// use OB on the whole page, or only go through the the_content ($renderingMode will be ignored)
|
13 |
+
public $isObMode = true;
|
14 |
+
// 'HtmlDomParser' (less prone to break badly formatted HTML) or 'DiDom' (faster)
|
15 |
+
public $parsingEngine = 'HtmlDomParser';
|
16 |
|
17 |
public function __construct() {
|
18 |
|
19 |
+
if ( is_admin() || $this->is_rest() ) {
|
20 |
return;
|
21 |
+
}
|
22 |
|
23 |
+
if ( $this->isObMode ) {
|
24 |
add_action( 'init', array( $this, 'start' ) );
|
25 |
add_action( 'shutdown', array( $this, 'shutdown' ) );
|
26 |
add_action( 'wp_footer', array( $this, 'unlink_lightboxes_script' ) ) ;
|
31 |
}
|
32 |
}
|
33 |
|
34 |
+
function is_rest() {
|
35 |
+
$prefix = rest_get_url_prefix( );
|
36 |
+
if ( defined( 'REST_REQUEST' ) && REST_REQUEST || isset( $_GET['rest_route'] ) &&
|
37 |
+
strpos( trim( $_GET['rest_route'], '\\/' ), $prefix , 0 ) === 0) {
|
38 |
+
return true;
|
39 |
+
}
|
40 |
+
|
41 |
+
// (#3)
|
42 |
+
$rest_url = wp_parse_url( site_url( $prefix ) );
|
43 |
+
$current_url = wp_parse_url( add_query_arg( array( ) ) );
|
44 |
+
return strpos( $current_url['path'], $rest_url['path'], 0 ) === 0;
|
45 |
+
}
|
46 |
+
|
47 |
+
function setOptions() {
|
48 |
+
$this->isObMode = get_option( 'mwl_obmode', $this->isObMode );
|
49 |
+
$this->parsingEngine = get_option( 'mwl_parsing_engine', $this->parsingEngine );
|
50 |
+
}
|
51 |
+
|
52 |
function init() {
|
53 |
//add_action( 'init', array( $this, 'init' ) );
|
54 |
// We don't need this now, we go through all the images.
|
58 |
|
59 |
function start() {
|
60 |
$this->isEnabled = apply_filters( 'gallery_custom_links_enabled', true );
|
61 |
+
if ( $this->isEnabled && $this->isObMode )
|
62 |
ob_start( array( $this, "linkify" ) );
|
63 |
}
|
64 |
|
105 |
if ( empty( $target ) )
|
106 |
$target = '_self';
|
107 |
$parent = $element->parent();
|
108 |
+
if ( $this->parsingEngine === 'HtmlDomParser' ) {
|
109 |
+
$src = $element->src;
|
110 |
+
$mglSrc = $element->{'mgl-src'};
|
111 |
+
if ( $parent->{'tag'} === 'figure' )
|
112 |
+
$parent = $parent->parent();
|
113 |
+
$a = new Element('a');
|
114 |
+
$a->{'href'} = $url;
|
115 |
+
$a->{'class'} = 'custom-link no-lightbox';
|
116 |
+
$a->{'onclick'} = 'event.stopPropagation()';
|
117 |
+
$a->{'target'} = $target;
|
118 |
+
$a->appendChild( $parent->children() );
|
119 |
+
foreach( $parent->children() as $img ) {
|
120 |
+
$img->remove();
|
121 |
}
|
122 |
+
$parent->appendChild( $a );
|
|
|
|
|
|
|
123 |
}
|
124 |
+
else {
|
125 |
+
if ( $parent->tag === 'figure' )
|
126 |
+
$parent = $parent->parent();
|
127 |
+
$a = new Element('a');
|
128 |
+
$a->attr( 'href', $url );
|
129 |
+
$a->attr( 'class', 'custom-link no-lightbox' );
|
130 |
+
$a->attr( 'onclick', 'event.stopPropagation()' );
|
131 |
+
$a->attr( 'target', $target );
|
132 |
+
$a->appendChild( $parent->children() );
|
133 |
+
foreach( $parent->children() as $img ) {
|
134 |
+
$img->remove();
|
135 |
+
}
|
136 |
+
$parent->appendChild( $a );
|
137 |
}
|
|
|
138 |
return true;
|
139 |
}
|
140 |
}
|
readme.txt
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
=== Gallery Custom Links ===
|
2 |
Contributors: TigrouMeow
|
3 |
Tags: custom, links, gallery, gutenberg
|
4 |
-
Requires at least:
|
5 |
-
Tested up to: 5.
|
6 |
Requires PHP: 7.0
|
7 |
-
Stable tag: 1.0.
|
8 |
|
9 |
Gallery Custom Links allows you to link images from galleries to a specified URL. Tested with WordPress Gallery, Gutenberg, the Meow Gallery and others.
|
10 |
|
@@ -41,6 +41,12 @@ Replace all the files. Nothing else to do.
|
|
41 |
|
42 |
== Changelog ==
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
= 1.0.8 =
|
45 |
* Update: Back to OB, maybe there should be an option for that.
|
46 |
* Update: Get all the images of the page/post content instead of within specific containers previously.
|
1 |
=== Gallery Custom Links ===
|
2 |
Contributors: TigrouMeow
|
3 |
Tags: custom, links, gallery, gutenberg
|
4 |
+
Requires at least: 5.0
|
5 |
+
Tested up to: 5.2
|
6 |
Requires PHP: 7.0
|
7 |
+
Stable tag: 1.0.9
|
8 |
|
9 |
Gallery Custom Links allows you to link images from galleries to a specified URL. Tested with WordPress Gallery, Gutenberg, the Meow Gallery and others.
|
10 |
|
41 |
|
42 |
== Changelog ==
|
43 |
|
44 |
+
= 1.0.9 =
|
45 |
+
* Info: This plugin is way more work than expected, please motivate me by giving it a good review and also my trying my other plugins (https://meowapps.com). Thanks a lot for that :) I will do my best to make this plugin perfect.
|
46 |
+
* Update: Avoid interfering at all with all Ajax/Rest requests.
|
47 |
+
* Update: Use HtmlDomParser instead of DiDom (this parser is less sensitive to badly formatted HTML). I am also thinking of doing it all with regexp, but let's see that later.
|
48 |
+
* Info: Sorry for the last bunch of updates, some way of modifying HTML works for some, and not for others, and I am still trying to find a solution which works for everyone.
|
49 |
+
|
50 |
= 1.0.8 =
|
51 |
* Update: Back to OB, maybe there should be an option for that.
|
52 |
* Update: Get all the images of the page/post content instead of within specific containers previously.
|
vendor/composer/autoload_namespaces.php
CHANGED
@@ -6,4 +6,5 @@ $vendorDir = dirname(dirname(__FILE__));
|
|
6 |
$baseDir = dirname($vendorDir);
|
7 |
|
8 |
return array(
|
|
|
9 |
);
|
6 |
$baseDir = dirname($vendorDir);
|
7 |
|
8 |
return array(
|
9 |
+
'KubAT\\PhpSimple\\HtmlDomParser' => array($vendorDir . '/kub-at/php-simple-html-dom-parser/src'),
|
10 |
);
|
vendor/composer/autoload_static.php
CHANGED
@@ -20,11 +20,22 @@ class ComposerStaticInit2605e89cef9fc84e4fbf6431ef455676
|
|
20 |
),
|
21 |
);
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
public static function getInitializer(ClassLoader $loader)
|
24 |
{
|
25 |
return \Closure::bind(function () use ($loader) {
|
26 |
$loader->prefixLengthsPsr4 = ComposerStaticInit2605e89cef9fc84e4fbf6431ef455676::$prefixLengthsPsr4;
|
27 |
$loader->prefixDirsPsr4 = ComposerStaticInit2605e89cef9fc84e4fbf6431ef455676::$prefixDirsPsr4;
|
|
|
28 |
|
29 |
}, null, ClassLoader::class);
|
30 |
}
|
20 |
),
|
21 |
);
|
22 |
|
23 |
+
public static $prefixesPsr0 = array (
|
24 |
+
'K' =>
|
25 |
+
array (
|
26 |
+
'KubAT\\PhpSimple\\HtmlDomParser' =>
|
27 |
+
array (
|
28 |
+
0 => __DIR__ . '/..' . '/kub-at/php-simple-html-dom-parser/src',
|
29 |
+
),
|
30 |
+
),
|
31 |
+
);
|
32 |
+
|
33 |
public static function getInitializer(ClassLoader $loader)
|
34 |
{
|
35 |
return \Closure::bind(function () use ($loader) {
|
36 |
$loader->prefixLengthsPsr4 = ComposerStaticInit2605e89cef9fc84e4fbf6431ef455676::$prefixLengthsPsr4;
|
37 |
$loader->prefixDirsPsr4 = ComposerStaticInit2605e89cef9fc84e4fbf6431ef455676::$prefixDirsPsr4;
|
38 |
+
$loader->prefixesPsr0 = ComposerStaticInit2605e89cef9fc84e4fbf6431ef455676::$prefixesPsr0;
|
39 |
|
40 |
}, null, ClassLoader::class);
|
41 |
}
|
vendor/composer/installed.json
CHANGED
@@ -49,5 +49,53 @@
|
|
49 |
"parser",
|
50 |
"xml"
|
51 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
]
|
49 |
"parser",
|
50 |
"xml"
|
51 |
]
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"name": "kub-at/php-simple-html-dom-parser",
|
55 |
+
"version": "1.7.1",
|
56 |
+
"version_normalized": "1.7.1.0",
|
57 |
+
"source": {
|
58 |
+
"type": "git",
|
59 |
+
"url": "https://github.com/Kub-AT/php-simple-html-dom-parser.git",
|
60 |
+
"reference": "7a745b20157efb0f1be3021394769bd6b8e9ed4e"
|
61 |
+
},
|
62 |
+
"dist": {
|
63 |
+
"type": "zip",
|
64 |
+
"url": "https://api.github.com/repos/Kub-AT/php-simple-html-dom-parser/zipball/7a745b20157efb0f1be3021394769bd6b8e9ed4e",
|
65 |
+
"reference": "7a745b20157efb0f1be3021394769bd6b8e9ed4e",
|
66 |
+
"shasum": ""
|
67 |
+
},
|
68 |
+
"require": {
|
69 |
+
"php": ">=5.3.2"
|
70 |
+
},
|
71 |
+
"time": "2019-01-02T14:33:28+00:00",
|
72 |
+
"type": "library",
|
73 |
+
"installation-source": "dist",
|
74 |
+
"autoload": {
|
75 |
+
"psr-0": {
|
76 |
+
"KubAT\\PhpSimple\\HtmlDomParser": "src/"
|
77 |
+
}
|
78 |
+
},
|
79 |
+
"notification-url": "https://packagist.org/downloads/",
|
80 |
+
"license": [
|
81 |
+
"MIT"
|
82 |
+
],
|
83 |
+
"authors": [
|
84 |
+
{
|
85 |
+
"name": "S.C. Chen",
|
86 |
+
"email": "me578022@gmail.com"
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"name": "Jakub Stawowy",
|
90 |
+
"email": "Kub-AT@users.noreply.github.com"
|
91 |
+
}
|
92 |
+
],
|
93 |
+
"description": "PHP Simple HTML DOM Parser with namespace and PHP 7.3 compatible",
|
94 |
+
"homepage": "http://simplehtmldom.sourceforge.net/",
|
95 |
+
"keywords": [
|
96 |
+
"Simple",
|
97 |
+
"dom",
|
98 |
+
"html"
|
99 |
+
]
|
100 |
}
|
101 |
]
|
vendor/kub-at/php-simple-html-dom-parser/CONTRIBUTING.md
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
# Contributing
|
2 |
+
|
3 |
+
I'm not the maintainer of the PHP Simple HTML DOM Parser project (https://sourceforge.net/projects/simplehtmldom/)
|
vendor/kub-at/php-simple-html-dom-parser/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
MIT License
|
2 |
+
|
3 |
+
Copyright (c) 2019 Jakub Stawowy
|
4 |
+
|
5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6 |
+
of this software and associated documentation files (the "Software"), to deal
|
7 |
+
in the Software without restriction, including without limitation the rights
|
8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9 |
+
copies of the Software, and to permit persons to whom the Software is
|
10 |
+
furnished to do so, subject to the following conditions:
|
11 |
+
|
12 |
+
The above copyright notice and this permission notice shall be included in all
|
13 |
+
copies or substantial portions of the Software.
|
14 |
+
|
15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
21 |
+
SOFTWARE.
|
vendor/kub-at/php-simple-html-dom-parser/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
php-simple-html-dom-parser
|
2 |
+
==========================
|
3 |
+
|
4 |
+
Version 1.7.1 - PHP 7.3 campatible
|
5 |
+
Changelog: https://sourceforge.net/projects/simplehtmldom/files/simplehtmldom/1.7/
|
6 |
+
|
7 |
+
|
8 |
+
Install
|
9 |
+
-------
|
10 |
+
|
11 |
+
```
|
12 |
+
composer require kub-at/php-simple-html-dom-parser
|
13 |
+
```
|
14 |
+
|
15 |
+
Usage
|
16 |
+
-----
|
17 |
+
|
18 |
+
```php
|
19 |
+
use KubAT\PhpSimple\HtmlDomParser;
|
20 |
+
|
21 |
+
...
|
22 |
+
$dom = HtmlDomParser::str_get_html( $str );
|
23 |
+
or
|
24 |
+
$dom = HtmlDomParser::file_get_html( $file_name );
|
25 |
+
|
26 |
+
$elems = $dom->find($elem_name);
|
27 |
+
...
|
28 |
+
|
29 |
+
```
|
vendor/kub-at/php-simple-html-dom-parser/composer.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name": "kub-at/php-simple-html-dom-parser",
|
3 |
+
"description": "PHP Simple HTML DOM Parser with namespace and PHP 7.3 compatible",
|
4 |
+
"keywords": ["html", "dom", "simple"],
|
5 |
+
"homepage": "http://simplehtmldom.sourceforge.net/",
|
6 |
+
"type": "library",
|
7 |
+
"license": "MIT",
|
8 |
+
"authors": [
|
9 |
+
{
|
10 |
+
"name": "S.C. Chen",
|
11 |
+
"email": "me578022@gmail.com"
|
12 |
+
},
|
13 |
+
{
|
14 |
+
"name": "Jakub Stawowy",
|
15 |
+
"email": "Kub-AT@users.noreply.github.com"
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"require": {
|
19 |
+
"php": ">=5.3.2"
|
20 |
+
},
|
21 |
+
"autoload": {
|
22 |
+
"psr-0": { "KubAT\\PhpSimple\\HtmlDomParser": "src/" }
|
23 |
+
}
|
24 |
+
}
|
vendor/kub-at/php-simple-html-dom-parser/src/KubAT/PhpSimple/HtmlDomParser.php
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?php
|
2 |
+
namespace KubAT\PhpSimple;
|
3 |
+
|
4 |
+
require 'lib'.DIRECTORY_SEPARATOR.'simple_html_dom.php';
|
5 |
+
|
6 |
+
|
7 |
+
class HtmlDomParser {
|
8 |
+
|
9 |
+
static public function file_get_html() {
|
10 |
+
return call_user_func_array('\simple_html_dom\file_get_html' , func_get_args());
|
11 |
+
}
|
12 |
+
|
13 |
+
static public function str_get_html() {
|
14 |
+
return call_user_func_array('\simple_html_dom\str_get_html' , func_get_args());
|
15 |
+
}
|
16 |
+
}
|
vendor/kub-at/php-simple-html-dom-parser/src/KubAT/PhpSimple/lib/simple_html_dom.php
ADDED
@@ -0,0 +1,2174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?php
|
2 |
+
namespace simple_html_dom;
|
3 |
+
|
4 |
+
/**
|
5 |
+
* Website: http://sourceforge.net/projects/simplehtmldom/
|
6 |
+
* Additional projects that may be used: http://sourceforge.net/projects/debugobject/
|
7 |
+
* Acknowledge: Jose Solorzano (https://sourceforge.net/projects/php-html/)
|
8 |
+
* Contributions by:
|
9 |
+
* Yousuke Kumakura (Attribute filters)
|
10 |
+
* Vadim Voituk (Negative indexes supports of "find" method)
|
11 |
+
* Antcs (Constructor with automatically load contents either text or file/url)
|
12 |
+
*
|
13 |
+
* all affected sections have comments starting with "PaperG"
|
14 |
+
*
|
15 |
+
* Paperg - Added case insensitive testing of the value of the selector.
|
16 |
+
* Paperg - Added tag_start for the starting index of tags - NOTE: This works but not accurately.
|
17 |
+
* This tag_start gets counted AFTER \r\n have been crushed out, and after the remove_noice calls so it will not reflect the REAL position of the tag in the source,
|
18 |
+
* it will almost always be smaller by some amount.
|
19 |
+
* We use this to determine how far into the file the tag in question is. This "percentage will never be accurate as the $dom->size is the "real" number of bytes the dom was created from.
|
20 |
+
* but for most purposes, it's a really good estimation.
|
21 |
+
* Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors.
|
22 |
+
* Allow the user to tell us how much they trust the html.
|
23 |
+
* Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node.
|
24 |
+
* This allows for us to find tags based on the text they contain.
|
25 |
+
* Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag.
|
26 |
+
* Paperg: added parse_charset so that we know about the character set of the source document.
|
27 |
+
* NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the
|
28 |
+
* last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection.
|
29 |
+
*
|
30 |
+
* Found infinite loop in the case of broken html in restore_noise. Rewrote to protect from that.
|
31 |
+
* PaperG (John Schlick) Added get_display_size for "IMG" tags.
|
32 |
+
*
|
33 |
+
* Licensed under The MIT License
|
34 |
+
* Redistributions of files must retain the above copyright notice.
|
35 |
+
*
|
36 |
+
* @author S.C. Chen <me578022@gmail.com>
|
37 |
+
* @author John Schlick
|
38 |
+
* @author Rus Carroll
|
39 |
+
* @version Rev. 1.7 (214)
|
40 |
+
* @package PlaceLocalInclude
|
41 |
+
* @subpackage simple_html_dom
|
42 |
+
*/
|
43 |
+
|
44 |
+
/**
|
45 |
+
* All of the Defines for the classes below.
|
46 |
+
* @author S.C. Chen <me578022@gmail.com>
|
47 |
+
*/
|
48 |
+
define('HDOM_TYPE_ELEMENT', 1);
|
49 |
+
define('HDOM_TYPE_COMMENT', 2);
|
50 |
+
define('HDOM_TYPE_TEXT', 3);
|
51 |
+
define('HDOM_TYPE_ENDTAG', 4);
|
52 |
+
define('HDOM_TYPE_ROOT', 5);
|
53 |
+
define('HDOM_TYPE_UNKNOWN', 6);
|
54 |
+
define('HDOM_QUOTE_DOUBLE', 0);
|
55 |
+
define('HDOM_QUOTE_SINGLE', 1);
|
56 |
+
define('HDOM_QUOTE_NO', 3);
|
57 |
+
define('HDOM_INFO_BEGIN', 0);
|
58 |
+
define('HDOM_INFO_END', 1);
|
59 |
+
define('HDOM_INFO_QUOTE', 2);
|
60 |
+
define('HDOM_INFO_SPACE', 3);
|
61 |
+
define('HDOM_INFO_TEXT', 4);
|
62 |
+
define('HDOM_INFO_INNER', 5);
|
63 |
+
define('HDOM_INFO_OUTER', 6);
|
64 |
+
define('HDOM_INFO_ENDSPACE',7);
|
65 |
+
define('DEFAULT_TARGET_CHARSET', 'UTF-8');
|
66 |
+
define('DEFAULT_BR_TEXT', "\r\n");
|
67 |
+
define('DEFAULT_SPAN_TEXT', " ");
|
68 |
+
define('MAX_FILE_SIZE', 600000);
|
69 |
+
|
70 |
+
/** Contents between curly braces "{" and "}" are interpreted as text */
|
71 |
+
define('HDOM_SMARTY_AS_TEXT', 1);
|
72 |
+
|
73 |
+
// helper functions
|
74 |
+
// -----------------------------------------------------------------------------
|
75 |
+
// get html dom from file
|
76 |
+
// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1.
|
77 |
+
function file_get_html($url, $use_include_path = false, $context=null, $offset = 0, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
|
78 |
+
{
|
79 |
+
// Ensure maximum length is greater than zero
|
80 |
+
if($maxLen <= 0) { $maxLen = MAX_FILE_SIZE; }
|
81 |
+
|
82 |
+
// We DO force the tags to be terminated.
|
83 |
+
$dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText);
|
84 |
+
// For sourceforge users: uncomment the next line and comment the retrieve_url_contents line 2 lines down if it is not already done.
|
85 |
+
$contents = file_get_contents($url, $use_include_path, $context, $offset, $maxLen);
|
86 |
+
// Paperg - use our own mechanism for getting the contents as we want to control the timeout.
|
87 |
+
//$contents = retrieve_url_contents($url);
|
88 |
+
if (empty($contents) || strlen($contents) > $maxLen)
|
89 |
+
{
|
90 |
+
return false;
|
91 |
+
}
|
92 |
+
// The second parameter can force the selectors to all be lowercase.
|
93 |
+
$dom->load($contents, $lowercase, $stripRN);
|
94 |
+
return $dom;
|
95 |
+
}
|
96 |
+
|
97 |
+
// get html dom from string
|
98 |
+
function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
|
99 |
+
{
|
100 |
+
$dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText);
|
101 |
+
if (empty($str) || strlen($str) > MAX_FILE_SIZE)
|
102 |
+
{
|
103 |
+
$dom->clear();
|
104 |
+
return false;
|
105 |
+
}
|
106 |
+
$dom->load($str, $lowercase, $stripRN);
|
107 |
+
return $dom;
|
108 |
+
}
|
109 |
+
|
110 |
+
// dump html dom tree
|
111 |
+
function dump_html_tree($node, $show_attr=true, $deep=0)
|
112 |
+
{
|
113 |
+
$node->dump($node);
|
114 |
+
}
|
115 |
+
|
116 |
+
|
117 |
+
/**
|
118 |
+
* simple html dom node
|
119 |
+
* PaperG - added ability for "find" routine to lowercase the value of the selector.
|
120 |
+
* PaperG - added $tag_start to track the start position of the tag in the total byte index
|
121 |
+
*
|
122 |
+
* @package PlaceLocalInclude
|
123 |
+
*/
|
124 |
+
class simple_html_dom_node
|
125 |
+
{
|
126 |
+
/**
|
127 |
+
* Node type
|
128 |
+
*
|
129 |
+
* Default is {@see HDOM_TYPE_TEXT}
|
130 |
+
*
|
131 |
+
* @var int
|
132 |
+
*/
|
133 |
+
public $nodetype = HDOM_TYPE_TEXT;
|
134 |
+
|
135 |
+
/**
|
136 |
+
* Tag name
|
137 |
+
*
|
138 |
+
* Default is 'text'
|
139 |
+
*
|
140 |
+
* @var string
|
141 |
+
*/
|
142 |
+
public $tag = 'text';
|
143 |
+
|
144 |
+
/**
|
145 |
+
* List of attributes
|
146 |
+
*
|
147 |
+
* @var array
|
148 |
+
*/
|
149 |
+
public $attr = array();
|
150 |
+
|
151 |
+
/**
|
152 |
+
* List of child node objects
|
153 |
+
*
|
154 |
+
* @var array
|
155 |
+
*/
|
156 |
+
public $children = array();
|
157 |
+
public $nodes = array();
|
158 |
+
|
159 |
+
/**
|
160 |
+
* The parent node object
|
161 |
+
*
|
162 |
+
* @var object|null
|
163 |
+
*/
|
164 |
+
public $parent = null;
|
165 |
+
|
166 |
+
// The "info" array - see HDOM_INFO_... for what each element contains.
|
167 |
+
public $_ = array();
|
168 |
+
|
169 |
+
/**
|
170 |
+
* Start position of the tag in the document
|
171 |
+
*
|
172 |
+
* @var int
|
173 |
+
*/
|
174 |
+
public $tag_start = 0;
|
175 |
+
|
176 |
+
/**
|
177 |
+
* The DOM object
|
178 |
+
*
|
179 |
+
* @var object|null
|
180 |
+
*/
|
181 |
+
private $dom = null;
|
182 |
+
|
183 |
+
/**
|
184 |
+
* Construct new node object
|
185 |
+
*
|
186 |
+
* Adds itself to the list of DOM Nodes {@see simple_html_dom::$nodes}
|
187 |
+
*/
|
188 |
+
function __construct($dom)
|
189 |
+
{
|
190 |
+
$this->dom = $dom;
|
191 |
+
$dom->nodes[] = $this;
|
192 |
+
}
|
193 |
+
|
194 |
+
function __destruct()
|
195 |
+
{
|
196 |
+
$this->clear();
|
197 |
+
}
|
198 |
+
|
199 |
+
function __toString()
|
200 |
+
{
|
201 |
+
return $this->outertext();
|
202 |
+
}
|
203 |
+
|
204 |
+
// clean up memory due to php5 circular references memory leak...
|
205 |
+
function clear()
|
206 |
+
{
|
207 |
+
$this->dom = null;
|
208 |
+
$this->nodes = null;
|
209 |
+
$this->parent = null;
|
210 |
+
$this->children = null;
|
211 |
+
}
|
212 |
+
|
213 |
+
// dump node's tree
|
214 |
+
function dump($show_attr=true, $deep=0)
|
215 |
+
{
|
216 |
+
$lead = str_repeat(' ', $deep);
|
217 |
+
|
218 |
+
echo $lead.$this->tag;
|
219 |
+
if ($show_attr && count($this->attr)>0)
|
220 |
+
{
|
221 |
+
echo '(';
|
222 |
+
foreach ($this->attr as $k=>$v)
|
223 |
+
echo "[$k]=>\"".$this->$k.'", ';
|
224 |
+
echo ')';
|
225 |
+
}
|
226 |
+
echo "\n";
|
227 |
+
|
228 |
+
if ($this->nodes)
|
229 |
+
{
|
230 |
+
foreach ($this->nodes as $c)
|
231 |
+
{
|
232 |
+
$c->dump($show_attr, $deep+1);
|
233 |
+
}
|
234 |
+
}
|
235 |
+
}
|
236 |
+
|
237 |
+
|
238 |
+
// Debugging function to dump a single dom node with a bunch of information about it.
|
239 |
+
function dump_node($echo=true)
|
240 |
+
{
|
241 |
+
|
242 |
+
$string = $this->tag;
|
243 |
+
if (count($this->attr)>0)
|
244 |
+
{
|
245 |
+
$string .= '(';
|
246 |
+
foreach ($this->attr as $k=>$v)
|
247 |
+
{
|
248 |
+
$string .= "[$k]=>\"".$this->$k.'", ';
|
249 |
+
}
|
250 |
+
$string .= ')';
|
251 |
+
}
|
252 |
+
if (count($this->_)>0)
|
253 |
+
{
|
254 |
+
$string .= ' $_ (';
|
255 |
+
foreach ($this->_ as $k=>$v)
|
256 |
+
{
|
257 |
+
if (is_array($v))
|
258 |
+
{
|
259 |
+
$string .= "[$k]=>(";
|
260 |
+
foreach ($v as $k2=>$v2)
|
261 |
+
{
|
262 |
+
$string .= "[$k2]=>\"".$v2.'", ';
|
263 |
+
}
|
264 |
+
$string .= ")";
|
265 |
+
} else {
|
266 |
+
$string .= "[$k]=>\"".$v.'", ';
|
267 |
+
}
|
268 |
+
}
|
269 |
+
$string .= ")";
|
270 |
+
}
|
271 |
+
|
272 |
+
if (isset($this->text))
|
273 |
+
{
|
274 |
+
$string .= " text: (" . $this->text . ")";
|
275 |
+
}
|
276 |
+
|
277 |
+
$string .= " HDOM_INNER_INFO: '";
|
278 |
+
if (isset($node->_[HDOM_INFO_INNER]))
|
279 |
+
{
|
280 |
+
$string .= $node->_[HDOM_INFO_INNER] . "'";
|
281 |
+
}
|
282 |
+
else
|
283 |
+
{
|
284 |
+
$string .= ' NULL ';
|
285 |
+
}
|
286 |
+
|
287 |
+
$string .= " children: " . count($this->children);
|
288 |
+
$string .= " nodes: " . count($this->nodes);
|
289 |
+
$string .= " tag_start: " . $this->tag_start;
|
290 |
+
$string .= "\n";
|
291 |
+
|
292 |
+
if ($echo)
|
293 |
+
{
|
294 |
+
echo $string;
|
295 |
+
return;
|
296 |
+
}
|
297 |
+
else
|
298 |
+
{
|
299 |
+
return $string;
|
300 |
+
}
|
301 |
+
}
|
302 |
+
|
303 |
+
/**
|
304 |
+
* Return or set parent node
|
305 |
+
*
|
306 |
+
* @param object|null $parent (optional) The parent node, `null` to return
|
307 |
+
* the current parent node.
|
308 |
+
* @return object|null The parent node
|
309 |
+
*/
|
310 |
+
function parent($parent=null)
|
311 |
+
{
|
312 |
+
// I am SURE that this doesn't work properly.
|
313 |
+
// It fails to unset the current node from it's current parents nodes or children list first.
|
314 |
+
if ($parent !== null)
|
315 |
+
{
|
316 |
+
$this->parent = $parent;
|
317 |
+
$this->parent->nodes[] = $this;
|
318 |
+
$this->parent->children[] = $this;
|
319 |
+
}
|
320 |
+
|
321 |
+
return $this->parent;
|
322 |
+
}
|
323 |
+
|
324 |
+
/**
|
325 |
+
* @return bool True if the node has at least one child node
|
326 |
+
*/
|
327 |
+
function has_child()
|
328 |
+
{
|
329 |
+
return !empty($this->children);
|
330 |
+
}
|
331 |
+
|
332 |
+
/**
|
333 |
+
* Get child node at specified index
|
334 |
+
*
|
335 |
+
* @param int $idx The index of the child node to return, `-1` to return all
|
336 |
+
* child nodes.
|
337 |
+
* @return object|array|null The child node at the specified index, all child
|
338 |
+
* nodes or null if the index is invalid.
|
339 |
+
*/
|
340 |
+
function children($idx=-1)
|
341 |
+
{
|
342 |
+
if ($idx===-1)
|
343 |
+
{
|
344 |
+
return $this->children;
|
345 |
+
}
|
346 |
+
if (isset($this->children[$idx]))
|
347 |
+
{
|
348 |
+
return $this->children[$idx];
|
349 |
+
}
|
350 |
+
return null;
|
351 |
+
}
|
352 |
+
|
353 |
+
/**
|
354 |
+
* Get first child node
|
355 |
+
*
|
356 |
+
* @return object|null The first child node or null if the current node has
|
357 |
+
* no child nodes.
|
358 |
+
*
|
359 |
+
* @todo Use `empty()` instead of `count()` to improve performance on large
|
360 |
+
* arrays.
|
361 |
+
*/
|
362 |
+
function first_child()
|
363 |
+
{
|
364 |
+
if (count($this->children)>0)
|
365 |
+
{
|
366 |
+
return $this->children[0];
|
367 |
+
}
|
368 |
+
return null;
|
369 |
+
}
|
370 |
+
|
371 |
+
/**
|
372 |
+
* Get last child node
|
373 |
+
*
|
374 |
+
* @return object|null The last child node or null if the current node has
|
375 |
+
* no child nodes.
|
376 |
+
*
|
377 |
+
* @todo Use `end()` to slightly improve performance on large arrays.
|
378 |
+
*/
|
379 |
+
function last_child()
|
380 |
+
{
|
381 |
+
if (($count=count($this->children))>0)
|
382 |
+
{
|
383 |
+
return $this->children[$count-1];
|
384 |
+
}
|
385 |
+
return null;
|
386 |
+
}
|
387 |
+
|
388 |
+
/**
|
389 |
+
* Get next sibling node
|
390 |
+
*
|
391 |
+
* @return object|null The sibling node or null if the current node has no
|
392 |
+
* sibling nodes.
|
393 |
+
*/
|
394 |
+
function next_sibling()
|
395 |
+
{
|
396 |
+
if ($this->parent===null)
|
397 |
+
{
|
398 |
+
return null;
|
399 |
+
}
|
400 |
+
|
401 |
+
$idx = 0;
|
402 |
+
$count = count($this->parent->children);
|
403 |
+
while ($idx<$count && $this!==$this->parent->children[$idx])
|
404 |
+
{
|
405 |
+
++$idx;
|
406 |
+
}
|
407 |
+
if (++$idx>=$count)
|
408 |
+
{
|
409 |
+
return null;
|
410 |
+
}
|
411 |
+
return $this->parent->children[$idx];
|
412 |
+
}
|
413 |
+
|
414 |
+
/**
|
415 |
+
* Get previous sibling node
|
416 |
+
*
|
417 |
+
* @return object|null The sibling node or null if the current node has no
|
418 |
+
* sibling nodes.
|
419 |
+
*/
|
420 |
+
function prev_sibling()
|
421 |
+
{
|
422 |
+
if ($this->parent===null) return null;
|
423 |
+
$idx = 0;
|
424 |
+
$count = count($this->parent->children);
|
425 |
+
while ($idx<$count && $this!==$this->parent->children[$idx])
|
426 |
+
++$idx;
|
427 |
+
if (--$idx<0) return null;
|
428 |
+
return $this->parent->children[$idx];
|
429 |
+
}
|
430 |
+
|
431 |
+
/**
|
432 |
+
* Traverse ancestors to the first matching tag.
|
433 |
+
*
|
434 |
+
* @param string $tag Tag to find
|
435 |
+
* @return object|null First matching node in the DOM tree or null if no
|
436 |
+
* match was found.
|
437 |
+
*
|
438 |
+
* @todo Null is returned implicitly by calling ->parent on the root node.
|
439 |
+
* This behaviour could change at any time, rendering this function invalid.
|
440 |
+
*/
|
441 |
+
function find_ancestor_tag($tag)
|
442 |
+
{
|
443 |
+
global $debug_object;
|
444 |
+
if (is_object($debug_object)) { $debug_object->debug_log_entry(1); }
|
445 |
+
|
446 |
+
// Start by including ourselves in the comparison.
|
447 |
+
$returnDom = $this;
|
448 |
+
|
449 |
+
while (!is_null($returnDom))
|
450 |
+
{
|
451 |
+
if (is_object($debug_object)) { $debug_object->debug_log(2, "Current tag is: " . $returnDom->tag); }
|
452 |
+
|
453 |
+
if ($returnDom->tag == $tag)
|
454 |
+
{
|
455 |
+
break;
|
456 |
+
}
|
457 |
+
$returnDom = $returnDom->parent;
|
458 |
+
}
|
459 |
+
return $returnDom;
|
460 |
+
}
|
461 |
+
|
462 |
+
/**
|
463 |
+
* Get node's inner text (everything inside the opening and closing tags)
|
464 |
+
*
|
465 |
+
* @return string
|
466 |
+
*/
|
467 |
+
function innertext()
|
468 |
+
{
|
469 |
+
if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER];
|
470 |
+
if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
|
471 |
+
|
472 |
+
$ret = '';
|
473 |
+
foreach ($this->nodes as $n)
|
474 |
+
$ret .= $n->outertext();
|
475 |
+
return $ret;
|
476 |
+
}
|
477 |
+
|
478 |
+
/**
|
479 |
+
* Get node's outer text (everything including the opening and closing tags)
|
480 |
+
*
|
481 |
+
* @return string
|
482 |
+
*/
|
483 |
+
function outertext()
|
484 |
+
{
|
485 |
+
global $debug_object;
|
486 |
+
if (is_object($debug_object))
|
487 |
+
{
|
488 |
+
$text = '';
|
489 |
+
if ($this->tag == 'text')
|
490 |
+
{
|
491 |
+
if (!empty($this->text))
|
492 |
+
{
|
493 |
+
$text = " with text: " . $this->text;
|
494 |
+
}
|
495 |
+
}
|
496 |
+
$debug_object->debug_log(1, 'Innertext of tag: ' . $this->tag . $text);
|
497 |
+
}
|
498 |
+
|
499 |
+
if ($this->tag==='root') return $this->innertext();
|
500 |
+
|
501 |
+
// trigger callback
|
502 |
+
if ($this->dom && $this->dom->callback!==null)
|
503 |
+
{
|
504 |
+
call_user_func_array($this->dom->callback, array($this));
|
505 |
+
}
|
506 |
+
|
507 |
+
if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER];
|
508 |
+
if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
|
509 |
+
|
510 |
+
// render begin tag
|
511 |
+
if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]])
|
512 |
+
{
|
513 |
+
$ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup();
|
514 |
+
} else {
|
515 |
+
$ret = "";
|
516 |
+
}
|
517 |
+
|
518 |
+
// render inner text
|
519 |
+
if (isset($this->_[HDOM_INFO_INNER]))
|
520 |
+
{
|
521 |
+
// If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added.
|
522 |
+
if ($this->tag != "br")
|
523 |
+
{
|
524 |
+
$ret .= $this->_[HDOM_INFO_INNER];
|
525 |
+
}
|
526 |
+
} else {
|
527 |
+
if ($this->nodes)
|
528 |
+
{
|
529 |
+
foreach ($this->nodes as $n)
|
530 |
+
{
|
531 |
+
$ret .= $this->convert_text($n->outertext());
|
532 |
+
}
|
533 |
+
}
|
534 |
+
}
|
535 |
+
|
536 |
+
// render end tag
|
537 |
+
if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0)
|
538 |
+
$ret .= '</'.$this->tag.'>';
|
539 |
+
return $ret;
|
540 |
+
}
|
541 |
+
|
542 |
+
/**
|
543 |
+
* Get node's plain text (everything excluding all tags)
|
544 |
+
*
|
545 |
+
* @return string
|
546 |
+
*/
|
547 |
+
function text()
|
548 |
+
{
|
549 |
+
if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER];
|
550 |
+
switch ($this->nodetype)
|
551 |
+
{
|
552 |
+
case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
|
553 |
+
case HDOM_TYPE_COMMENT: return '';
|
554 |
+
case HDOM_TYPE_UNKNOWN: return '';
|
555 |
+
}
|
556 |
+
if (strcasecmp($this->tag, 'script')===0) return '';
|
557 |
+
if (strcasecmp($this->tag, 'style')===0) return '';
|
558 |
+
|
559 |
+
$ret = '';
|
560 |
+
// In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL.
|
561 |
+
// NOTE: This indicates that there is a problem where it's set to NULL without a clear happening.
|
562 |
+
// WHY is this happening?
|
563 |
+
if (!is_null($this->nodes))
|
564 |
+
{
|
565 |
+
foreach ($this->nodes as $n)
|
566 |
+
{
|
567 |
+
// Start paragraph after a blank line
|
568 |
+
if ($n->tag == 'p')
|
569 |
+
{
|
570 |
+
$ret .= "\n\n";
|
571 |
+
}
|
572 |
+
|
573 |
+
$ret .= $this->convert_text($n->text());
|
574 |
+
|
575 |
+
// If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all.
|
576 |
+
if ($n->tag == "span")
|
577 |
+
{
|
578 |
+
$ret .= $this->dom->default_span_text;
|
579 |
+
}
|
580 |
+
}
|
581 |
+
}
|
582 |
+
return trim($ret);
|
583 |
+
}
|
584 |
+
|
585 |
+
/**
|
586 |
+
* Get node's xml text (inner text as a CDATA section)
|
587 |
+
*
|
588 |
+
* @return string
|
589 |
+
*/
|
590 |
+
function xmltext()
|
591 |
+
{
|
592 |
+
$ret = $this->innertext();
|
593 |
+
$ret = str_ireplace('<![CDATA[', '', $ret);
|
594 |
+
$ret = str_replace(']]>', '', $ret);
|
595 |
+
return $ret;
|
596 |
+
}
|
597 |
+
|
598 |
+
// build node's text with tag
|
599 |
+
function makeup()
|
600 |
+
{
|
601 |
+
// text, comment, unknown
|
602 |
+
if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
|
603 |
+
|
604 |
+
$ret = '<'.$this->tag;
|
605 |
+
$i = -1;
|
606 |
+
|
607 |
+
foreach ($this->attr as $key=>$val)
|
608 |
+
{
|
609 |
+
++$i;
|
610 |
+
|
611 |
+
// skip removed attribute
|
612 |
+
if ($val===null || $val===false)
|
613 |
+
continue;
|
614 |
+
|
615 |
+
$ret .= $this->_[HDOM_INFO_SPACE][$i][0];
|
616 |
+
//no value attr: nowrap, checked selected...
|
617 |
+
if ($val===true)
|
618 |
+
$ret .= $key;
|
619 |
+
else {
|
620 |
+
switch ($this->_[HDOM_INFO_QUOTE][$i])
|
621 |
+
{
|
622 |
+
case HDOM_QUOTE_DOUBLE: $quote = '"'; break;
|
623 |
+
case HDOM_QUOTE_SINGLE: $quote = '\''; break;
|
624 |
+
default: $quote = '';
|
625 |
+
}
|
626 |
+
$ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote;
|
627 |
+
}
|
628 |
+
}
|
629 |
+
$ret = $this->dom->restore_noise($ret);
|
630 |
+
return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>';
|
631 |
+
}
|
632 |
+
|
633 |
+
// find elements by css selector
|
634 |
+
//PaperG - added ability for find to lowercase the value of the selector.
|
635 |
+
function find($selector, $idx=null, $lowercase=false)
|
636 |
+
{
|
637 |
+
$selectors = $this->parse_selector($selector);
|
638 |
+
if (($count=count($selectors))===0) return array();
|
639 |
+
$found_keys = array();
|
640 |
+
|
641 |
+
// find each selector
|
642 |
+
for ($c=0; $c<$count; ++$c)
|
643 |
+
{
|
644 |
+
// The change on the below line was documented on the sourceforge code tracker id 2788009
|
645 |
+
// used to be: if (($levle=count($selectors[0]))===0) return array();
|
646 |
+
if (($levle=count($selectors[$c]))===0) return array();
|
647 |
+
if (!isset($this->_[HDOM_INFO_BEGIN])) return array();
|
648 |
+
|
649 |
+
$head = array($this->_[HDOM_INFO_BEGIN]=>1);
|
650 |
+
|
651 |
+
// handle descendant selectors, no recursive!
|
652 |
+
for ($l=0; $l<$levle; ++$l)
|
653 |
+
{
|
654 |
+
$ret = array();
|
655 |
+
foreach ($head as $k=>$v)
|
656 |
+
{
|
657 |
+
$n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k];
|
658 |
+
//PaperG - Pass this optional parameter on to the seek function.
|
659 |
+
$n->seek($selectors[$c][$l], $ret, $lowercase);
|
660 |
+
}
|
661 |
+
$head = $ret;
|
662 |
+
}
|
663 |
+
|
664 |
+
foreach ($head as $k=>$v)
|
665 |
+
{
|
666 |
+
if (!isset($found_keys[$k]))
|
667 |
+
{
|
668 |
+
$found_keys[$k] = 1;
|
669 |
+
}
|
670 |
+
}
|
671 |
+
}
|
672 |
+
|
673 |
+
// sort keys
|
674 |
+
ksort($found_keys);
|
675 |
+
|
676 |
+
$found = array();
|
677 |
+
foreach ($found_keys as $k=>$v)
|
678 |
+
$found[] = $this->dom->nodes[$k];
|
679 |
+
|
680 |
+
// return nth-element or array
|
681 |
+
if (is_null($idx)) return $found;
|
682 |
+
else if ($idx<0) $idx = count($found) + $idx;
|
683 |
+
return (isset($found[$idx])) ? $found[$idx] : null;
|
684 |
+
}
|
685 |
+
|
686 |
+
// seek for given conditions
|
687 |
+
// PaperG - added parameter to allow for case insensitive testing of the value of a selector.
|
688 |
+
protected function seek($selector, &$ret, $lowercase=false)
|
689 |
+
{
|
690 |
+
global $debug_object;
|
691 |
+
if (is_object($debug_object)) { $debug_object->debug_log_entry(1); }
|
692 |
+
|
693 |
+
list($tag, $key, $val, $exp, $no_key) = $selector;
|
694 |
+
|
695 |
+
// xpath index
|
696 |
+
if ($tag && $key && is_numeric($key))
|
697 |
+
{
|
698 |
+
$count = 0;
|
699 |
+
foreach ($this->children as $c)
|
700 |
+
{
|
701 |
+
if ($tag==='*' || $tag===$c->tag) {
|
702 |
+
if (++$count==$key) {
|
703 |
+
$ret[$c->_[HDOM_INFO_BEGIN]] = 1;
|
704 |
+
return;
|
705 |
+
}
|
706 |
+
}
|
707 |
+
}
|
708 |
+
return;
|
709 |
+
}
|
710 |
+
|
711 |
+
$end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0;
|
712 |
+
if ($end==0) {
|
713 |
+
$parent = $this->parent;
|
714 |
+
while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) {
|
715 |
+
$end -= 1;
|
716 |
+
$parent = $parent->parent;
|
717 |
+
}
|
718 |
+
$end += $parent->_[HDOM_INFO_END];
|
719 |
+
}
|
720 |
+
|
721 |
+
for ($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) {
|
722 |
+
$node = $this->dom->nodes[$i];
|
723 |
+
|
724 |
+
$pass = true;
|
725 |
+
|
726 |
+
if ($tag==='*' && !$key) {
|
727 |
+
if (in_array($node, $this->children, true))
|
728 |
+
$ret[$i] = 1;
|
729 |
+
continue;
|
730 |
+
}
|
731 |
+
|
732 |
+
// compare tag
|
733 |
+
if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;}
|
734 |
+
// compare key
|
735 |
+
if ($pass && $key) {
|
736 |
+
if ($no_key) {
|
737 |
+
if (isset($node->attr[$key])) $pass=false;
|
738 |
+
} else {
|
739 |
+
if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false;
|
740 |
+
}
|
741 |
+
}
|
742 |
+
// compare value
|
743 |
+
if ($pass && $key && $val && $val!=='*') {
|
744 |
+
// If they have told us that this is a "plaintext" search then we want the plaintext of the node - right?
|
745 |
+
if ($key == "plaintext") {
|
746 |
+
// $node->plaintext actually returns $node->text();
|
747 |
+
$nodeKeyValue = $node->text();
|
748 |
+
} else {
|
749 |
+
// this is a normal search, we want the value of that attribute of the tag.
|
750 |
+
$nodeKeyValue = $node->attr[$key];
|
751 |
+
}
|
752 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);}
|
753 |
+
|
754 |
+
//PaperG - If lowercase is set, do a case insensitive test of the value of the selector.
|
755 |
+
if ($lowercase) {
|
756 |
+
$check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue));
|
757 |
+
} else {
|
758 |
+
$check = $this->match($exp, $val, $nodeKeyValue);
|
759 |
+
}
|
760 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, "after match: " . ($check ? "true" : "false"));}
|
761 |
+
|
762 |
+
// handle multiple class
|
763 |
+
if (!$check && strcasecmp($key, 'class')===0) {
|
764 |
+
foreach (explode(' ',$node->attr[$key]) as $k) {
|
765 |
+
// Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form.
|
766 |
+
if (!empty($k)) {
|
767 |
+
if ($lowercase) {
|
768 |
+
$check = $this->match($exp, strtolower($val), strtolower($k));
|
769 |
+
} else {
|
770 |
+
$check = $this->match($exp, $val, $k);
|
771 |
+
}
|
772 |
+
if ($check) break;
|
773 |
+
}
|
774 |
+
}
|
775 |
+
}
|
776 |
+
if (!$check) $pass = false;
|
777 |
+
}
|
778 |
+
if ($pass) $ret[$i] = 1;
|
779 |
+
unset($node);
|
780 |
+
}
|
781 |
+
// It's passed by reference so this is actually what this function returns.
|
782 |
+
if (is_object($debug_object)) {$debug_object->debug_log(1, "EXIT - ret: ", $ret);}
|
783 |
+
}
|
784 |
+
|
785 |
+
protected function match($exp, $pattern, $value) {
|
786 |
+
global $debug_object;
|
787 |
+
if (is_object($debug_object)) {$debug_object->debug_log_entry(1);}
|
788 |
+
|
789 |
+
switch ($exp) {
|
790 |
+
case '=':
|
791 |
+
return ($value===$pattern);
|
792 |
+
case '!=':
|
793 |
+
return ($value!==$pattern);
|
794 |
+
case '^=':
|
795 |
+
return preg_match("/^".preg_quote($pattern,'/')."/", $value);
|
796 |
+
case '$=':
|
797 |
+
return preg_match("/".preg_quote($pattern,'/')."$/", $value);
|
798 |
+
case '*=':
|
799 |
+
if ($pattern[0]=='/') {
|
800 |
+
return preg_match($pattern, $value);
|
801 |
+
}
|
802 |
+
return preg_match("/".$pattern."/i", $value);
|
803 |
+
}
|
804 |
+
return false;
|
805 |
+
}
|
806 |
+
|
807 |
+
protected function parse_selector($selector_string) {
|
808 |
+
global $debug_object;
|
809 |
+
if (is_object($debug_object)) {$debug_object->debug_log_entry(1);}
|
810 |
+
|
811 |
+
// pattern of CSS selectors, modified from mootools
|
812 |
+
// Paperg: Add the colon to the attrbute, so that it properly finds <tag attr:ibute="something" > like google does.
|
813 |
+
// Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check.
|
814 |
+
// Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured.
|
815 |
+
// This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression.
|
816 |
+
// farther study is required to determine of this should be documented or removed.
|
817 |
+
// $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
|
818 |
+
$pattern = "/([\w:\*-]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w:-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
|
819 |
+
preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER);
|
820 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, "Matches Array: ", $matches);}
|
821 |
+
|
822 |
+
$selectors = array();
|
823 |
+
$result = array();
|
824 |
+
//print_r($matches);
|
825 |
+
|
826 |
+
foreach ($matches as $m) {
|
827 |
+
$m[0] = trim($m[0]);
|
828 |
+
if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue;
|
829 |
+
// for browser generated xpath
|
830 |
+
if ($m[1]==='tbody') continue;
|
831 |
+
|
832 |
+
list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false);
|
833 |
+
if (!empty($m[2])) {$key='id'; $val=$m[2];}
|
834 |
+
if (!empty($m[3])) {$key='class'; $val=$m[3];}
|
835 |
+
if (!empty($m[4])) {$key=$m[4];}
|
836 |
+
if (!empty($m[5])) {$exp=$m[5];}
|
837 |
+
if (!empty($m[6])) {$val=$m[6];}
|
838 |
+
|
839 |
+
// convert to lowercase
|
840 |
+
if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);}
|
841 |
+
//elements that do NOT have the specified attribute
|
842 |
+
if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;}
|
843 |
+
|
844 |
+
$result[] = array($tag, $key, $val, $exp, $no_key);
|
845 |
+
if (trim($m[7])===',') {
|
846 |
+
$selectors[] = $result;
|
847 |
+
$result = array();
|
848 |
+
}
|
849 |
+
}
|
850 |
+
if (count($result)>0)
|
851 |
+
$selectors[] = $result;
|
852 |
+
return $selectors;
|
853 |
+
}
|
854 |
+
|
855 |
+
function __get($name)
|
856 |
+
{
|
857 |
+
if (isset($this->attr[$name]))
|
858 |
+
{
|
859 |
+
return $this->convert_text($this->attr[$name]);
|
860 |
+
}
|
861 |
+
switch ($name)
|
862 |
+
{
|
863 |
+
case 'outertext': return $this->outertext();
|
864 |
+
case 'innertext': return $this->innertext();
|
865 |
+
case 'plaintext': return $this->text();
|
866 |
+
case 'xmltext': return $this->xmltext();
|
867 |
+
default: return array_key_exists($name, $this->attr);
|
868 |
+
}
|
869 |
+
}
|
870 |
+
|
871 |
+
function __set($name, $value)
|
872 |
+
{
|
873 |
+
global $debug_object;
|
874 |
+
if (is_object($debug_object)) {$debug_object->debug_log_entry(1);}
|
875 |
+
|
876 |
+
switch ($name)
|
877 |
+
{
|
878 |
+
case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value;
|
879 |
+
case 'innertext':
|
880 |
+
if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value;
|
881 |
+
return $this->_[HDOM_INFO_INNER] = $value;
|
882 |
+
}
|
883 |
+
if (!isset($this->attr[$name]))
|
884 |
+
{
|
885 |
+
$this->_[HDOM_INFO_SPACE][] = array(' ', '', '');
|
886 |
+
$this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE;
|
887 |
+
}
|
888 |
+
$this->attr[$name] = $value;
|
889 |
+
}
|
890 |
+
|
891 |
+
function __isset($name)
|
892 |
+
{
|
893 |
+
switch ($name)
|
894 |
+
{
|
895 |
+
case 'outertext': return true;
|
896 |
+
case 'innertext': return true;
|
897 |
+
case 'plaintext': return true;
|
898 |
+
}
|
899 |
+
//no value attr: nowrap, checked selected...
|
900 |
+
return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]);
|
901 |
+
}
|
902 |
+
|
903 |
+
function __unset($name) {
|
904 |
+
if (isset($this->attr[$name]))
|
905 |
+
unset($this->attr[$name]);
|
906 |
+
}
|
907 |
+
|
908 |
+
// PaperG - Function to convert the text from one character set to another if the two sets are not the same.
|
909 |
+
function convert_text($text)
|
910 |
+
{
|
911 |
+
global $debug_object;
|
912 |
+
if (is_object($debug_object)) {$debug_object->debug_log_entry(1);}
|
913 |
+
|
914 |
+
$converted_text = $text;
|
915 |
+
|
916 |
+
$sourceCharset = "";
|
917 |
+
$targetCharset = "";
|
918 |
+
|
919 |
+
if ($this->dom)
|
920 |
+
{
|
921 |
+
$sourceCharset = strtoupper($this->dom->_charset);
|
922 |
+
$targetCharset = strtoupper($this->dom->_target_charset);
|
923 |
+
}
|
924 |
+
if (is_object($debug_object)) {$debug_object->debug_log(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);}
|
925 |
+
|
926 |
+
if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0))
|
927 |
+
{
|
928 |
+
// Check if the reported encoding could have been incorrect and the text is actually already UTF-8
|
929 |
+
if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text)))
|
930 |
+
{
|
931 |
+
$converted_text = $text;
|
932 |
+
}
|
933 |
+
else
|
934 |
+
{
|
935 |
+
$converted_text = iconv($sourceCharset, $targetCharset, $text);
|
936 |
+
}
|
937 |
+
}
|
938 |
+
|
939 |
+
// Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output.
|
940 |
+
if ($targetCharset == 'UTF-8')
|
941 |
+
{
|
942 |
+
if (substr($converted_text, 0, 3) == "\xef\xbb\xbf")
|
943 |
+
{
|
944 |
+
$converted_text = substr($converted_text, 3);
|
945 |
+
}
|
946 |
+
if (substr($converted_text, -3) == "\xef\xbb\xbf")
|
947 |
+
{
|
948 |
+
$converted_text = substr($converted_text, 0, -3);
|
949 |
+
}
|
950 |
+
}
|
951 |
+
|
952 |
+
return $converted_text;
|
953 |
+
}
|
954 |
+
|
955 |
+
/**
|
956 |
+
* Returns true if $string is valid UTF-8 and false otherwise.
|
957 |
+
*
|
958 |
+
* @param mixed $str String to be tested
|
959 |
+
* @return boolean
|
960 |
+
*/
|
961 |
+
static function is_utf8($str)
|
962 |
+
{
|
963 |
+
$c=0; $b=0;
|
964 |
+
$bits=0;
|
965 |
+
$len=strlen($str);
|
966 |
+
for($i=0; $i<$len; $i++)
|
967 |
+
{
|
968 |
+
$c=ord($str[$i]);
|
969 |
+
if($c > 128)
|
970 |
+
{
|
971 |
+
if(($c >= 254)) return false;
|
972 |
+
elseif($c >= 252) $bits=6;
|
973 |
+
elseif($c >= 248) $bits=5;
|
974 |
+
elseif($c >= 240) $bits=4;
|
975 |
+
elseif($c >= 224) $bits=3;
|
976 |
+
elseif($c >= 192) $bits=2;
|
977 |
+
else return false;
|
978 |
+
if(($i+$bits) > $len) return false;
|
979 |
+
while($bits > 1)
|
980 |
+
{
|
981 |
+
$i++;
|
982 |
+
$b=ord($str[$i]);
|
983 |
+
if($b < 128 || $b > 191) return false;
|
984 |
+
$bits--;
|
985 |
+
}
|
986 |
+
}
|
987 |
+
}
|
988 |
+
return true;
|
989 |
+
}
|
990 |
+
/*
|
991 |
+
function is_utf8($string)
|
992 |
+
{
|
993 |
+
//this is buggy
|
994 |
+
return (utf8_encode(utf8_decode($string)) == $string);
|
995 |
+
}
|
996 |
+
*/
|
997 |
+
|
998 |
+
/**
|
999 |
+
* Function to try a few tricks to determine the displayed size of an img on the page.
|
1000 |
+
* NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types.
|
1001 |
+
*
|
1002 |
+
* @author John Schlick
|
1003 |
+
* @version April 19 2012
|
1004 |
+
* @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out.
|
1005 |
+
*/
|
1006 |
+
function get_display_size()
|
1007 |
+
{
|
1008 |
+
global $debug_object;
|
1009 |
+
|
1010 |
+
$width = -1;
|
1011 |
+
$height = -1;
|
1012 |
+
|
1013 |
+
if ($this->tag !== 'img')
|
1014 |
+
{
|
1015 |
+
return false;
|
1016 |
+
}
|
1017 |
+
|
1018 |
+
// See if there is aheight or width attribute in the tag itself.
|
1019 |
+
if (isset($this->attr['width']))
|
1020 |
+
{
|
1021 |
+
$width = $this->attr['width'];
|
1022 |
+
}
|
1023 |
+
|
1024 |
+
if (isset($this->attr['height']))
|
1025 |
+
{
|
1026 |
+
$height = $this->attr['height'];
|
1027 |
+
}
|
1028 |
+
|
1029 |
+
// Now look for an inline style.
|
1030 |
+
if (isset($this->attr['style']))
|
1031 |
+
{
|
1032 |
+
// Thanks to user gnarf from stackoverflow for this regular expression.
|
1033 |
+
$attributes = array();
|
1034 |
+
preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER);
|
1035 |
+
foreach ($matches as $match) {
|
1036 |
+
$attributes[$match[1]] = $match[2];
|
1037 |
+
}
|
1038 |
+
|
1039 |
+
// If there is a width in the style attributes:
|
1040 |
+
if (isset($attributes['width']) && $width == -1)
|
1041 |
+
{
|
1042 |
+
// check that the last two characters are px (pixels)
|
1043 |
+
if (strtolower(substr($attributes['width'], -2)) == 'px')
|
1044 |
+
{
|
1045 |
+
$proposed_width = substr($attributes['width'], 0, -2);
|
1046 |
+
// Now make sure that it's an integer and not something stupid.
|
1047 |
+
if (filter_var($proposed_width, FILTER_VALIDATE_INT))
|
1048 |
+
{
|
1049 |
+
$width = $proposed_width;
|
1050 |
+
}
|
1051 |
+
}
|
1052 |
+
}
|
1053 |
+
|
1054 |
+
// If there is a width in the style attributes:
|
1055 |
+
if (isset($attributes['height']) && $height == -1)
|
1056 |
+
{
|
1057 |
+
// check that the last two characters are px (pixels)
|
1058 |
+
if (strtolower(substr($attributes['height'], -2)) == 'px')
|
1059 |
+
{
|
1060 |
+
$proposed_height = substr($attributes['height'], 0, -2);
|
1061 |
+
// Now make sure that it's an integer and not something stupid.
|
1062 |
+
if (filter_var($proposed_height, FILTER_VALIDATE_INT))
|
1063 |
+
{
|
1064 |
+
$height = $proposed_height;
|
1065 |
+
}
|
1066 |
+
}
|
1067 |
+
}
|
1068 |
+
|
1069 |
+
}
|
1070 |
+
|
1071 |
+
// Future enhancement:
|
1072 |
+
// Look in the tag to see if there is a class or id specified that has a height or width attribute to it.
|
1073 |
+
|
1074 |
+
// Far future enhancement
|
1075 |
+
// Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width
|
1076 |
+
// Note that in this case, the class or id will have the img subselector for it to apply to the image.
|
1077 |
+
|
1078 |
+
// ridiculously far future development
|
1079 |
+
// If the class or id is specified in a SEPARATE css file thats not on the page, go get it and do what we were just doing for the ones on the page.
|
1080 |
+
|
1081 |
+
$result = array('height' => $height,
|
1082 |
+
'width' => $width);
|
1083 |
+
return $result;
|
1084 |
+
}
|
1085 |
+
|
1086 |
+
// camel naming conventions
|
1087 |
+
function getAllAttributes() {return $this->attr;}
|
1088 |
+
function getAttribute($name) {return $this->__get($name);}
|
1089 |
+
function setAttribute($name, $value) {$this->__set($name, $value);}
|
1090 |
+
function hasAttribute($name) {return $this->__isset($name);}
|
1091 |
+
function removeAttribute($name) {$this->__set($name, null);}
|
1092 |
+
function getElementById($id) {return $this->find("#$id", 0);}
|
1093 |
+
function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);}
|
1094 |
+
function getElementByTagName($name) {return $this->find($name, 0);}
|
1095 |
+
function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);}
|
1096 |
+
function parentNode() {return $this->parent();}
|
1097 |
+
function childNodes($idx=-1) {return $this->children($idx);}
|
1098 |
+
function firstChild() {return $this->first_child();}
|
1099 |
+
function lastChild() {return $this->last_child();}
|
1100 |
+
function nextSibling() {return $this->next_sibling();}
|
1101 |
+
function previousSibling() {return $this->prev_sibling();}
|
1102 |
+
function hasChildNodes() {return $this->has_child();}
|
1103 |
+
function nodeName() {return $this->tag;}
|
1104 |
+
function appendChild($node) {$node->parent($this); return $node;}
|
1105 |
+
|
1106 |
+
}
|
1107 |
+
|
1108 |
+
/**
|
1109 |
+
* simple html dom parser
|
1110 |
+
* Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector.
|
1111 |
+
* Paperg - change $size from protected to public so we can easily access it
|
1112 |
+
* Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it.
|
1113 |
+
*
|
1114 |
+
* @package PlaceLocalInclude
|
1115 |
+
*/
|
1116 |
+
class simple_html_dom
|
1117 |
+
{
|
1118 |
+
/**
|
1119 |
+
* The root node of the document
|
1120 |
+
*
|
1121 |
+
* @var object
|
1122 |
+
*/
|
1123 |
+
public $root = null;
|
1124 |
+
|
1125 |
+
/**
|
1126 |
+
* List of nodes in the current DOM
|
1127 |
+
*
|
1128 |
+
* @var array
|
1129 |
+
*/
|
1130 |
+
public $nodes = array();
|
1131 |
+
|
1132 |
+
/**
|
1133 |
+
* Callback function to run for each element in the DOM.
|
1134 |
+
*
|
1135 |
+
* @var callable|null
|
1136 |
+
*/
|
1137 |
+
public $callback = null;
|
1138 |
+
|
1139 |
+
/**
|
1140 |
+
* Indicates how tags and attributes are matched
|
1141 |
+
*
|
1142 |
+
* @var bool When set to **true** tags and attributes will be converted to
|
1143 |
+
* lowercase before matching.
|
1144 |
+
*/
|
1145 |
+
public $lowercase = false;
|
1146 |
+
|
1147 |
+
/**
|
1148 |
+
* Original document size
|
1149 |
+
*
|
1150 |
+
* Holds the original document size.
|
1151 |
+
*
|
1152 |
+
* @var int
|
1153 |
+
*/
|
1154 |
+
public $original_size;
|
1155 |
+
|
1156 |
+
/**
|
1157 |
+
* Current document size
|
1158 |
+
*
|
1159 |
+
* Holds the current document size. The document size is determined by the
|
1160 |
+
* string length of ({@see simple_html_dom::$doc}).
|
1161 |
+
*
|
1162 |
+
* _Note_: Using this variable is more efficient than calling `strlen($doc)`
|
1163 |
+
*
|
1164 |
+
* @var int
|
1165 |
+
* */
|
1166 |
+
public $size;
|
1167 |
+
|
1168 |
+
/**
|
1169 |
+
* Current position in the document
|
1170 |
+
*
|
1171 |
+
* @var int
|
1172 |
+
*/
|
1173 |
+
protected $pos;
|
1174 |
+
|
1175 |
+
/**
|
1176 |
+
* The document
|
1177 |
+
*
|
1178 |
+
* @var string
|
1179 |
+
*/
|
1180 |
+
protected $doc;
|
1181 |
+
|
1182 |
+
/**
|
1183 |
+
* Current character
|
1184 |
+
*
|
1185 |
+
* Holds the current character at position {@see simple_html_dom::$pos} in
|
1186 |
+
* the document {@see simple_html_dom::$doc}
|
1187 |
+
*
|
1188 |
+
* _Note_: Using this variable is more efficient than calling `substr($doc, $pos, 1)`
|
1189 |
+
*
|
1190 |
+
* @var string
|
1191 |
+
*/
|
1192 |
+
protected $char;
|
1193 |
+
|
1194 |
+
protected $cursor;
|
1195 |
+
|
1196 |
+
/**
|
1197 |
+
* Parent node of the next node detected by the parser
|
1198 |
+
*
|
1199 |
+
* @var object
|
1200 |
+
*/
|
1201 |
+
protected $parent;
|
1202 |
+
protected $noise = array();
|
1203 |
+
|
1204 |
+
/**
|
1205 |
+
* Tokens considered blank in HTML
|
1206 |
+
*
|
1207 |
+
* @var string
|
1208 |
+
*/
|
1209 |
+
protected $token_blank = " \t\r\n";
|
1210 |
+
|
1211 |
+
/**
|
1212 |
+
* Tokens to identify the equal sign for attributes, stopping either at the
|
1213 |
+
* closing tag ("/" i.e. "<html />") or the end of an opening tag (">" i.e.
|
1214 |
+
* "<html>")
|
1215 |
+
*
|
1216 |
+
* @var string
|
1217 |
+
*/
|
1218 |
+
protected $token_equal = ' =/>';
|
1219 |
+
|
1220 |
+
/**
|
1221 |
+
* Tokens to identify the end of a tag name. A tag name either ends on the
|
1222 |
+
* ending slash ("/" i.e. "<html/>") or whitespace ("\s\r\n\t")
|
1223 |
+
*
|
1224 |
+
* @var string
|
1225 |
+
*/
|
1226 |
+
protected $token_slash = " />\r\n\t";
|
1227 |
+
|
1228 |
+
/**
|
1229 |
+
* Tokens to identify the end of an attribute
|
1230 |
+
*
|
1231 |
+
* @var string
|
1232 |
+
*/
|
1233 |
+
protected $token_attr = ' >';
|
1234 |
+
|
1235 |
+
// Note that this is referenced by a child node, and so it needs to be public for that node to see this information.
|
1236 |
+
public $_charset = '';
|
1237 |
+
public $_target_charset = '';
|
1238 |
+
|
1239 |
+
/**
|
1240 |
+
* Innertext for <br> elements
|
1241 |
+
*
|
1242 |
+
* @var string
|
1243 |
+
*/
|
1244 |
+
protected $default_br_text = "";
|
1245 |
+
|
1246 |
+
/**
|
1247 |
+
* Suffix for <span> elements
|
1248 |
+
*
|
1249 |
+
* @var string
|
1250 |
+
*/
|
1251 |
+
public $default_span_text = "";
|
1252 |
+
|
1253 |
+
/**
|
1254 |
+
* Defines a list of self-closing tags (Void elements) according to the HTML
|
1255 |
+
* Specification
|
1256 |
+
*
|
1257 |
+
* _Remarks_:
|
1258 |
+
* - Use `isset()` instead of `in_array()` on array elements to boost
|
1259 |
+
* performance about 30%
|
1260 |
+
* - Sort elements by name for better readability!
|
1261 |
+
*
|
1262 |
+
* @link https://www.w3.org/TR/html HTML Specification
|
1263 |
+
* @link https://www.w3.org/TR/html/syntax.html#void-elements Void elements
|
1264 |
+
*/
|
1265 |
+
protected $self_closing_tags = array(
|
1266 |
+
'area'=>1,
|
1267 |
+
'base'=>1,
|
1268 |
+
'br'=>1,
|
1269 |
+
'col'=>1,
|
1270 |
+
'embed'=>1,
|
1271 |
+
'hr'=>1,
|
1272 |
+
'img'=>1,
|
1273 |
+
'input'=>1,
|
1274 |
+
'link'=>1,
|
1275 |
+
'meta'=>1,
|
1276 |
+
'param'=>1,
|
1277 |
+
'source'=>1,
|
1278 |
+
'track'=>1,
|
1279 |
+
'wbr'=>1
|
1280 |
+
);
|
1281 |
+
|
1282 |
+
/**
|
1283 |
+
* Defines a list of tags which - if closed - close all optional closing
|
1284 |
+
* elements within if they haven't been closed yet. (So, an element where
|
1285 |
+
* neither opening nor closing tag is omissible consistently closes every
|
1286 |
+
* optional closing element within)
|
1287 |
+
*
|
1288 |
+
* _Remarks_:
|
1289 |
+
* - Use `isset()` instead of `in_array()` on array elements to boost
|
1290 |
+
* performance about 30%
|
1291 |
+
* - Sort elements by name for better readability!
|
1292 |
+
*/
|
1293 |
+
protected $block_tags = array(
|
1294 |
+
'body'=>1,
|
1295 |
+
'div'=>1,
|
1296 |
+
'form'=>1,
|
1297 |
+
'root'=>1,
|
1298 |
+
'span'=>1,
|
1299 |
+
'table'=>1
|
1300 |
+
);
|
1301 |
+
|
1302 |
+
/**
|
1303 |
+
* Defines elements whose end tag is omissible.
|
1304 |
+
*
|
1305 |
+
* * key = Name of an element whose end tag is omissible.
|
1306 |
+
* * value = Names of elements whose end tag is omissible, that are closed
|
1307 |
+
* by the current element.
|
1308 |
+
*
|
1309 |
+
* _Remarks_:
|
1310 |
+
* - Use `isset()` instead of `in_array()` on array elements to boost
|
1311 |
+
* performance about 30%
|
1312 |
+
* - Sort elements by name for better readability!
|
1313 |
+
*
|
1314 |
+
* **Example**
|
1315 |
+
*
|
1316 |
+
* An `li` element’s end tag may be omitted if the `li` element is immediately
|
1317 |
+
* followed by another `li` element. To do that, add following element to the
|
1318 |
+
* array:
|
1319 |
+
*
|
1320 |
+
* ```php
|
1321 |
+
* 'li' => array('li'),
|
1322 |
+
* ```
|
1323 |
+
*
|
1324 |
+
* With this, the following two examples are considered equal. Note that the
|
1325 |
+
* second example is missing the closing tags on `li` elements.
|
1326 |
+
*
|
1327 |
+
* ```html
|
1328 |
+
* <ul><li>First Item</li><li>Second Item</li></ul>
|
1329 |
+
* ```
|
1330 |
+
*
|
1331 |
+
* <ul><li>First Item</li><li>Second Item</li></ul>
|
1332 |
+
*
|
1333 |
+
* ```html
|
1334 |
+
* <ul><li>First Item<li>Second Item</ul>
|
1335 |
+
* ```
|
1336 |
+
*
|
1337 |
+
* <ul><li>First Item<li>Second Item</ul>
|
1338 |
+
*
|
1339 |
+
* @var array A two-dimensional array where the key is the name of an
|
1340 |
+
* element whose end tag is omissible and the value is an array of elements
|
1341 |
+
* whose end tag is omissible, that are closed by the current element.
|
1342 |
+
*
|
1343 |
+
* @link https://www.w3.org/TR/html/syntax.html#optional-tags Optional tags
|
1344 |
+
*
|
1345 |
+
* @todo The implementation of optional closing tags doesn't work in all cases
|
1346 |
+
* because it only consideres elements who close other optional closing
|
1347 |
+
* tags, not taking into account that some (non-blocking) tags should close
|
1348 |
+
* these optional closing tags. For example, the end tag for "p" is omissible
|
1349 |
+
* and can be closed by an "address" element, whose end tag is NOT omissible.
|
1350 |
+
* Currently a "p" element without closing tag stops at the next "p" element
|
1351 |
+
* or blocking tag, even if it contains other elements.
|
1352 |
+
*
|
1353 |
+
* @todo Known sourceforge issue #2977341
|
1354 |
+
* B tags that are not closed cause us to return everything to the end of
|
1355 |
+
* the document.
|
1356 |
+
*/
|
1357 |
+
protected $optional_closing_tags = array(
|
1358 |
+
'b'=>array('b'=>1), // Not optional, see https://www.w3.org/TR/html/textlevel-semantics.html#the-b-element
|
1359 |
+
'dd'=>array('dd'=>1, 'dt'=>1),
|
1360 |
+
'dl'=>array('dd'=>1, 'dt'=>1), // Not optional, see https://www.w3.org/TR/html/grouping-content.html#the-dl-element
|
1361 |
+
'dt'=>array('dd'=>1, 'dt'=>1),
|
1362 |
+
'li'=>array('li'=>1),
|
1363 |
+
'optgroup'=>array('optgroup'=>1, 'option'=>1),
|
1364 |
+
'option'=>array('optgroup'=>1, 'option'=>1),
|
1365 |
+
'p'=>array('p'=>1),
|
1366 |
+
'rp'=>array('rp'=>1, 'rt'=>1),
|
1367 |
+
'rt'=>array('rp'=>1, 'rt'=>1),
|
1368 |
+
'td'=>array('td'=>1, 'th'=>1),
|
1369 |
+
'th'=>array('td'=>1, 'th'=>1),
|
1370 |
+
'tr'=>array('td'=>1, 'th'=>1, 'tr'=>1),
|
1371 |
+
);
|
1372 |
+
|
1373 |
+
function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT, $options=0)
|
1374 |
+
{
|
1375 |
+
if ($str)
|
1376 |
+
{
|
1377 |
+
if (preg_match("/^http:\/\//i",$str) || is_file($str))
|
1378 |
+
{
|
1379 |
+
$this->load_file($str);
|
1380 |
+
}
|
1381 |
+
else
|
1382 |
+
{
|
1383 |
+
$this->load($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText, $options);
|
1384 |
+
}
|
1385 |
+
}
|
1386 |
+
// Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html.
|
1387 |
+
if (!$forceTagsClosed) {
|
1388 |
+
$this->optional_closing_array=array();
|
1389 |
+
}
|
1390 |
+
$this->_target_charset = $target_charset;
|
1391 |
+
}
|
1392 |
+
|
1393 |
+
function __destruct()
|
1394 |
+
{
|
1395 |
+
$this->clear();
|
1396 |
+
}
|
1397 |
+
|
1398 |
+
// load html from string
|
1399 |
+
function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT, $options=0)
|
1400 |
+
{
|
1401 |
+
global $debug_object;
|
1402 |
+
|
1403 |
+
// prepare
|
1404 |
+
$this->prepare($str, $lowercase, $defaultBRText, $defaultSpanText);
|
1405 |
+
|
1406 |
+
// Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037
|
1407 |
+
// Script tags removal now preceeds style tag removal.
|
1408 |
+
// strip out <script> tags
|
1409 |
+
$this->remove_noise("'<\s*script[^>]*[^/]>(.*?)<\s*/\s*script\s*>'is");
|
1410 |
+
$this->remove_noise("'<\s*script\s*>(.*?)<\s*/\s*script\s*>'is");
|
1411 |
+
|
1412 |
+
// strip out the \r \n's if we are told to.
|
1413 |
+
if ($stripRN) {
|
1414 |
+
$this->doc = str_replace("\r", " ", $this->doc);
|
1415 |
+
$this->doc = str_replace("\n", " ", $this->doc);
|
1416 |
+
|
1417 |
+
// set the length of content since we have changed it.
|
1418 |
+
$this->size = strlen($this->doc);
|
1419 |
+
}
|
1420 |
+
|
1421 |
+
// strip out cdata
|
1422 |
+
$this->remove_noise("'<!\[CDATA\[(.*?)\]\]>'is", true);
|
1423 |
+
// strip out comments
|
1424 |
+
$this->remove_noise("'<!--(.*?)-->'is");
|
1425 |
+
// strip out <style> tags
|
1426 |
+
$this->remove_noise("'<\s*style[^>]*[^/]>(.*?)<\s*/\s*style\s*>'is");
|
1427 |
+
$this->remove_noise("'<\s*style\s*>(.*?)<\s*/\s*style\s*>'is");
|
1428 |
+
// strip out preformatted tags
|
1429 |
+
$this->remove_noise("'<\s*(?:code)[^>]*>(.*?)<\s*/\s*(?:code)\s*>'is");
|
1430 |
+
// strip out server side scripts
|
1431 |
+
$this->remove_noise("'(<\?)(.*?)(\?>)'s", true);
|
1432 |
+
|
1433 |
+
if($options & HDOM_SMARTY_AS_TEXT) { // Strip Smarty scripts
|
1434 |
+
$this->remove_noise("'(\{\w)(.*?)(\})'s", true);
|
1435 |
+
}
|
1436 |
+
|
1437 |
+
// parsing
|
1438 |
+
$this->parse();
|
1439 |
+
// end
|
1440 |
+
$this->root->_[HDOM_INFO_END] = $this->cursor;
|
1441 |
+
$this->parse_charset();
|
1442 |
+
|
1443 |
+
// make load function chainable
|
1444 |
+
return $this;
|
1445 |
+
|
1446 |
+
}
|
1447 |
+
|
1448 |
+
// load html from file
|
1449 |
+
function load_file()
|
1450 |
+
{
|
1451 |
+
$args = func_get_args();
|
1452 |
+
|
1453 |
+
if($doc = call_user_func_array('file_get_contents', $args) !== false) {
|
1454 |
+
$this->load($doc, true);
|
1455 |
+
} else {
|
1456 |
+
return false;
|
1457 |
+
}
|
1458 |
+
}
|
1459 |
+
|
1460 |
+
/**
|
1461 |
+
* Set the callback function
|
1462 |
+
*
|
1463 |
+
* @param callable $function_name Callback function to run for each element
|
1464 |
+
* in the DOM.
|
1465 |
+
* @return void
|
1466 |
+
*/
|
1467 |
+
function set_callback($function_name)
|
1468 |
+
{
|
1469 |
+
$this->callback = $function_name;
|
1470 |
+
}
|
1471 |
+
|
1472 |
+
/**
|
1473 |
+
* Remove callback function
|
1474 |
+
*
|
1475 |
+
* @return void
|
1476 |
+
*/
|
1477 |
+
function remove_callback()
|
1478 |
+
{
|
1479 |
+
$this->callback = null;
|
1480 |
+
}
|
1481 |
+
|
1482 |
+
// save dom as string
|
1483 |
+
function save($filepath='')
|
1484 |
+
{
|
1485 |
+
$ret = $this->root->innertext();
|
1486 |
+
if ($filepath!=='') file_put_contents($filepath, $ret, LOCK_EX);
|
1487 |
+
return $ret;
|
1488 |
+
}
|
1489 |
+
|
1490 |
+
// find dom node by css selector
|
1491 |
+
// Paperg - allow us to specify that we want case insensitive testing of the value of the selector.
|
1492 |
+
function find($selector, $idx=null, $lowercase=false)
|
1493 |
+
{
|
1494 |
+
return $this->root->find($selector, $idx, $lowercase);
|
1495 |
+
}
|
1496 |
+
|
1497 |
+
// clean up memory due to php5 circular references memory leak...
|
1498 |
+
function clear()
|
1499 |
+
{
|
1500 |
+
foreach ($this->nodes as $n) {$n->clear(); $n = null;}
|
1501 |
+
// This add next line is documented in the sourceforge repository. 2977248 as a fix for ongoing memory leaks that occur even with the use of clear.
|
1502 |
+
if (isset($this->children)) foreach ($this->children as $n) {$n->clear(); $n = null;}
|
1503 |
+
if (isset($this->parent)) {$this->parent->clear(); unset($this->parent);}
|
1504 |
+
if (isset($this->root)) {$this->root->clear(); unset($this->root);}
|
1505 |
+
unset($this->doc);
|
1506 |
+
unset($this->noise);
|
1507 |
+
}
|
1508 |
+
|
1509 |
+
function dump($show_attr=true)
|
1510 |
+
{
|
1511 |
+
$this->root->dump($show_attr);
|
1512 |
+
}
|
1513 |
+
|
1514 |
+
// prepare HTML data and init everything
|
1515 |
+
protected function prepare($str, $lowercase=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
|
1516 |
+
{
|
1517 |
+
$this->clear();
|
1518 |
+
|
1519 |
+
$this->doc = trim($str);
|
1520 |
+
$this->size = strlen($this->doc);
|
1521 |
+
$this->original_size = $this->size; // Save the original size of the html that we got in. It might be useful to someone.
|
1522 |
+
$this->pos = 0;
|
1523 |
+
$this->cursor = 1;
|
1524 |
+
$this->noise = array();
|
1525 |
+
$this->nodes = array();
|
1526 |
+
$this->lowercase = $lowercase;
|
1527 |
+
$this->default_br_text = $defaultBRText;
|
1528 |
+
$this->default_span_text = $defaultSpanText;
|
1529 |
+
$this->root = new simple_html_dom_node($this);
|
1530 |
+
$this->root->tag = 'root';
|
1531 |
+
$this->root->_[HDOM_INFO_BEGIN] = -1;
|
1532 |
+
$this->root->nodetype = HDOM_TYPE_ROOT;
|
1533 |
+
$this->parent = $this->root;
|
1534 |
+
if ($this->size>0) $this->char = $this->doc[0];
|
1535 |
+
}
|
1536 |
+
|
1537 |
+
/**
|
1538 |
+
* Parse HTML content
|
1539 |
+
*
|
1540 |
+
* @return bool True on success
|
1541 |
+
*/
|
1542 |
+
protected function parse()
|
1543 |
+
{
|
1544 |
+
while (true) {
|
1545 |
+
// Read next tag if there is no text between current position and the
|
1546 |
+
// next opening tag.
|
1547 |
+
if (($s = $this->copy_until_char('<'))==='')
|
1548 |
+
{
|
1549 |
+
if($this->read_tag()) {
|
1550 |
+
continue;
|
1551 |
+
} else {
|
1552 |
+
return true;
|
1553 |
+
}
|
1554 |
+
}
|
1555 |
+
|
1556 |
+
// Add a text node for text between tags
|
1557 |
+
$node = new simple_html_dom_node($this);
|
1558 |
+
++$this->cursor;
|
1559 |
+
$node->_[HDOM_INFO_TEXT] = $s;
|
1560 |
+
$this->link_nodes($node, false);
|
1561 |
+
}
|
1562 |
+
}
|
1563 |
+
|
1564 |
+
// PAPERG - dkchou - added this to try to identify the character set of the page we have just parsed so we know better how to spit it out later.
|
1565 |
+
// NOTE: IF you provide a routine called get_last_retrieve_url_contents_content_type which returns the CURLINFO_CONTENT_TYPE from the last curl_exec
|
1566 |
+
// (or the content_type header from the last transfer), we will parse THAT, and if a charset is specified, we will use it over any other mechanism.
|
1567 |
+
protected function parse_charset()
|
1568 |
+
{
|
1569 |
+
global $debug_object;
|
1570 |
+
|
1571 |
+
$charset = null;
|
1572 |
+
|
1573 |
+
if (function_exists('get_last_retrieve_url_contents_content_type'))
|
1574 |
+
{
|
1575 |
+
$contentTypeHeader = get_last_retrieve_url_contents_content_type();
|
1576 |
+
$success = preg_match('/charset=(.+)/', $contentTypeHeader, $matches);
|
1577 |
+
if ($success)
|
1578 |
+
{
|
1579 |
+
$charset = $matches[1];
|
1580 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, 'header content-type found charset of: ' . $charset);}
|
1581 |
+
}
|
1582 |
+
|
1583 |
+
}
|
1584 |
+
|
1585 |
+
if (empty($charset))
|
1586 |
+
{
|
1587 |
+
$el = $this->root->find('meta[http-equiv=Content-Type]',0, true);
|
1588 |
+
if (!empty($el))
|
1589 |
+
{
|
1590 |
+
$fullvalue = $el->content;
|
1591 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, 'meta content-type tag found' . $fullvalue);}
|
1592 |
+
|
1593 |
+
if (!empty($fullvalue))
|
1594 |
+
{
|
1595 |
+
$success = preg_match('/charset=(.+)/i', $fullvalue, $matches);
|
1596 |
+
if ($success)
|
1597 |
+
{
|
1598 |
+
$charset = $matches[1];
|
1599 |
+
}
|
1600 |
+
else
|
1601 |
+
{
|
1602 |
+
// If there is a meta tag, and they don't specify the character set, research says that it's typically ISO-8859-1
|
1603 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, 'meta content-type tag couldn\'t be parsed. using iso-8859 default.');}
|
1604 |
+
$charset = 'ISO-8859-1';
|
1605 |
+
}
|
1606 |
+
}
|
1607 |
+
}
|
1608 |
+
}
|
1609 |
+
|
1610 |
+
// If we couldn't find a charset above, then lets try to detect one based on the text we got...
|
1611 |
+
if (empty($charset))
|
1612 |
+
{
|
1613 |
+
// Use this in case mb_detect_charset isn't installed/loaded on this machine.
|
1614 |
+
$charset = false;
|
1615 |
+
if (function_exists('mb_detect_encoding'))
|
1616 |
+
{
|
1617 |
+
// Have php try to detect the encoding from the text given to us.
|
1618 |
+
$charset = mb_detect_encoding($this->doc . "ascii", $encoding_list = array( "UTF-8", "CP1252" ) );
|
1619 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, 'mb_detect found: ' . $charset);}
|
1620 |
+
}
|
1621 |
+
|
1622 |
+
// and if this doesn't work... then we need to just wrongheadedly assume it's UTF-8 so that we can move on - cause this will usually give us most of what we need...
|
1623 |
+
if ($charset === false)
|
1624 |
+
{
|
1625 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, 'since mb_detect failed - using default of utf-8');}
|
1626 |
+
$charset = 'UTF-8';
|
1627 |
+
}
|
1628 |
+
}
|
1629 |
+
|
1630 |
+
// Since CP1252 is a superset, if we get one of it's subsets, we want it instead.
|
1631 |
+
if ((strtolower($charset) == strtolower('ISO-8859-1')) || (strtolower($charset) == strtolower('Latin1')) || (strtolower($charset) == strtolower('Latin-1')))
|
1632 |
+
{
|
1633 |
+
if (is_object($debug_object)) {$debug_object->debug_log(2, 'replacing ' . $charset . ' with CP1252 as its a superset');}
|
1634 |
+
$charset = 'CP1252';
|
1635 |
+
}
|
1636 |
+
|
1637 |
+
if (is_object($debug_object)) {$debug_object->debug_log(1, 'EXIT - ' . $charset);}
|
1638 |
+
|
1639 |
+
return $this->_charset = $charset;
|
1640 |
+
}
|
1641 |
+
|
1642 |
+
/**
|
1643 |
+
* Parse tag from current document position.
|
1644 |
+
*
|
1645 |
+
* @return bool True if a tag was found, false otherwise
|
1646 |
+
*/
|
1647 |
+
protected function read_tag()
|
1648 |
+
{
|
1649 |
+
// Set end position if no further tags found
|
1650 |
+
if ($this->char!=='<')
|
1651 |
+
{
|
1652 |
+
$this->root->_[HDOM_INFO_END] = $this->cursor;
|
1653 |
+
return false;
|
1654 |
+
}
|
1655 |
+
$begin_tag_pos = $this->pos;
|
1656 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1657 |
+
|
1658 |
+
// end tag
|
1659 |
+
if ($this->char==='/')
|
1660 |
+
{
|
1661 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1662 |
+
|
1663 |
+
// Skip whitespace in end tags (i.e. in "</ html>")
|
1664 |
+
$this->skip($this->token_blank);
|
1665 |
+
$tag = $this->copy_until_char('>');
|
1666 |
+
|
1667 |
+
// Skip attributes in end tags
|
1668 |
+
if (($pos = strpos($tag, ' '))!==false)
|
1669 |
+
$tag = substr($tag, 0, $pos);
|
1670 |
+
|
1671 |
+
$parent_lower = strtolower($this->parent->tag);
|
1672 |
+
$tag_lower = strtolower($tag);
|
1673 |
+
|
1674 |
+
// The end tag is supposed to close the parent tag. Handle situations
|
1675 |
+
// when it doesn't
|
1676 |
+
if ($parent_lower!==$tag_lower)
|
1677 |
+
{
|
1678 |
+
// Parent tag does not have to be closed necessarily (optional closing tag)
|
1679 |
+
// Current tag is a block tag, so it may close an ancestor
|
1680 |
+
if (isset($this->optional_closing_tags[$parent_lower]) && isset($this->block_tags[$tag_lower]))
|
1681 |
+
{
|
1682 |
+
$this->parent->_[HDOM_INFO_END] = 0;
|
1683 |
+
$org_parent = $this->parent;
|
1684 |
+
|
1685 |
+
// Traverse ancestors to find a matching opening tag
|
1686 |
+
// Stop at root node
|
1687 |
+
while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower)
|
1688 |
+
$this->parent = $this->parent->parent;
|
1689 |
+
|
1690 |
+
// If we don't have a match add current tag as text node
|
1691 |
+
if (strtolower($this->parent->tag)!==$tag_lower) {
|
1692 |
+
$this->parent = $org_parent; // restore origonal parent
|
1693 |
+
if ($this->parent->parent) $this->parent = $this->parent->parent;
|
1694 |
+
$this->parent->_[HDOM_INFO_END] = $this->cursor;
|
1695 |
+
return $this->as_text_node($tag);
|
1696 |
+
}
|
1697 |
+
}
|
1698 |
+
// Grandparent exists and current tag is a block tag, so our parent doesn't have an end tag
|
1699 |
+
else if (($this->parent->parent) && isset($this->block_tags[$tag_lower]))
|
1700 |
+
{
|
1701 |
+
$this->parent->_[HDOM_INFO_END] = 0; // No end tag
|
1702 |
+
$org_parent = $this->parent;
|
1703 |
+
|
1704 |
+
// Traverse ancestors to find a matching opening tag
|
1705 |
+
// Stop at root node
|
1706 |
+
while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower)
|
1707 |
+
$this->parent = $this->parent->parent;
|
1708 |
+
|
1709 |
+
// If we don't have a match add current tag as text node
|
1710 |
+
if (strtolower($this->parent->tag)!==$tag_lower)
|
1711 |
+
{
|
1712 |
+
$this->parent = $org_parent; // restore origonal parent
|
1713 |
+
$this->parent->_[HDOM_INFO_END] = $this->cursor;
|
1714 |
+
return $this->as_text_node($tag);
|
1715 |
+
}
|
1716 |
+
}
|
1717 |
+
// Grandparent exists and current tag closes it
|
1718 |
+
else if (($this->parent->parent) && strtolower($this->parent->parent->tag)===$tag_lower)
|
1719 |
+
{
|
1720 |
+
$this->parent->_[HDOM_INFO_END] = 0;
|
1721 |
+
$this->parent = $this->parent->parent;
|
1722 |
+
}
|
1723 |
+
else // Random tag, add as text node
|
1724 |
+
return $this->as_text_node($tag);
|
1725 |
+
}
|
1726 |
+
|
1727 |
+
// Set end position of parent tag to current cursor position
|
1728 |
+
$this->parent->_[HDOM_INFO_END] = $this->cursor;
|
1729 |
+
if ($this->parent->parent) $this->parent = $this->parent->parent;
|
1730 |
+
|
1731 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1732 |
+
return true;
|
1733 |
+
}
|
1734 |
+
|
1735 |
+
// start tag
|
1736 |
+
$node = new simple_html_dom_node($this);
|
1737 |
+
$node->_[HDOM_INFO_BEGIN] = $this->cursor;
|
1738 |
+
++$this->cursor;
|
1739 |
+
$tag = $this->copy_until($this->token_slash); // Get tag name
|
1740 |
+
$node->tag_start = $begin_tag_pos;
|
1741 |
+
|
1742 |
+
// doctype, cdata & comments...
|
1743 |
+
// <!DOCTYPE html>
|
1744 |
+
// <![CDATA[ ... ]]>
|
1745 |
+
// <!-- Comment -->
|
1746 |
+
if (isset($tag[0]) && $tag[0]==='!') {
|
1747 |
+
$node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until_char('>');
|
1748 |
+
|
1749 |
+
if (isset($tag[2]) && $tag[1]==='-' && $tag[2]==='-') { // Comment ("<!--")
|
1750 |
+
$node->nodetype = HDOM_TYPE_COMMENT;
|
1751 |
+
$node->tag = 'comment';
|
1752 |
+
} else { // Could be doctype or CDATA but we don't care
|
1753 |
+
$node->nodetype = HDOM_TYPE_UNKNOWN;
|
1754 |
+
$node->tag = 'unknown';
|
1755 |
+
}
|
1756 |
+
if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>';
|
1757 |
+
$this->link_nodes($node, true);
|
1758 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1759 |
+
return true;
|
1760 |
+
}
|
1761 |
+
|
1762 |
+
// The start tag cannot contain another start tag, if so add as text
|
1763 |
+
// i.e. "<<html>"
|
1764 |
+
if ($pos=strpos($tag, '<')!==false) {
|
1765 |
+
$tag = '<' . substr($tag, 0, -1);
|
1766 |
+
$node->_[HDOM_INFO_TEXT] = $tag;
|
1767 |
+
$this->link_nodes($node, false);
|
1768 |
+
$this->char = $this->doc[--$this->pos]; // prev
|
1769 |
+
return true;
|
1770 |
+
}
|
1771 |
+
|
1772 |
+
// Handle invalid tag names (i.e. "<html#doc>")
|
1773 |
+
if (!preg_match("/^\w[\w:-]*$/", $tag)) {
|
1774 |
+
$node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until('<>');
|
1775 |
+
|
1776 |
+
// Next char is the beginning of a new tag, don't touch it.
|
1777 |
+
if ($this->char==='<') {
|
1778 |
+
$this->link_nodes($node, false);
|
1779 |
+
return true;
|
1780 |
+
}
|
1781 |
+
|
1782 |
+
// Next char closes current tag, add and be done with it.
|
1783 |
+
if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>';
|
1784 |
+
$this->link_nodes($node, false);
|
1785 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1786 |
+
return true;
|
1787 |
+
}
|
1788 |
+
|
1789 |
+
// begin tag, add new node
|
1790 |
+
$node->nodetype = HDOM_TYPE_ELEMENT;
|
1791 |
+
$tag_lower = strtolower($tag);
|
1792 |
+
$node->tag = ($this->lowercase) ? $tag_lower : $tag;
|
1793 |
+
|
1794 |
+
// handle optional closing tags
|
1795 |
+
if (isset($this->optional_closing_tags[$tag_lower]) )
|
1796 |
+
{
|
1797 |
+
// Traverse ancestors to close all optional closing tags
|
1798 |
+
while (isset($this->optional_closing_tags[$tag_lower][strtolower($this->parent->tag)]))
|
1799 |
+
{
|
1800 |
+
$this->parent->_[HDOM_INFO_END] = 0;
|
1801 |
+
$this->parent = $this->parent->parent;
|
1802 |
+
}
|
1803 |
+
$node->parent = $this->parent;
|
1804 |
+
}
|
1805 |
+
|
1806 |
+
$guard = 0; // prevent infinity loop
|
1807 |
+
$space = array($this->copy_skip($this->token_blank), '', ''); // [0] Space between tag and first attribute
|
1808 |
+
|
1809 |
+
// attributes
|
1810 |
+
do
|
1811 |
+
{
|
1812 |
+
// Everything until the first equal sign should be the attribute name
|
1813 |
+
$name = $this->copy_until($this->token_equal);
|
1814 |
+
|
1815 |
+
if ($name==='' && $this->char!==null && $space[0]==='')
|
1816 |
+
{
|
1817 |
+
break;
|
1818 |
+
}
|
1819 |
+
|
1820 |
+
if ($guard===$this->pos) // Escape infinite loop
|
1821 |
+
{
|
1822 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1823 |
+
continue;
|
1824 |
+
}
|
1825 |
+
$guard = $this->pos;
|
1826 |
+
|
1827 |
+
// handle endless '<'
|
1828 |
+
if ($this->pos>=$this->size-1 && $this->char!=='>') { // Out of bounds before the tag ended
|
1829 |
+
$node->nodetype = HDOM_TYPE_TEXT;
|
1830 |
+
$node->_[HDOM_INFO_END] = 0;
|
1831 |
+
$node->_[HDOM_INFO_TEXT] = '<'.$tag . $space[0] . $name;
|
1832 |
+
$node->tag = 'text';
|
1833 |
+
$this->link_nodes($node, false);
|
1834 |
+
return true;
|
1835 |
+
}
|
1836 |
+
|
1837 |
+
// handle mismatch '<'
|
1838 |
+
if ($this->doc[$this->pos-1]=='<') { // Attributes cannot start after opening tag
|
1839 |
+
$node->nodetype = HDOM_TYPE_TEXT;
|
1840 |
+
$node->tag = 'text';
|
1841 |
+
$node->attr = array();
|
1842 |
+
$node->_[HDOM_INFO_END] = 0;
|
1843 |
+
$node->_[HDOM_INFO_TEXT] = substr($this->doc, $begin_tag_pos, $this->pos-$begin_tag_pos-1);
|
1844 |
+
$this->pos -= 2;
|
1845 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1846 |
+
$this->link_nodes($node, false);
|
1847 |
+
return true;
|
1848 |
+
}
|
1849 |
+
|
1850 |
+
if ($name!=='/' && $name!=='') { // this is a attribute name
|
1851 |
+
$space[1] = $this->copy_skip($this->token_blank); // [1] Whitespace after attribute name
|
1852 |
+
$name = $this->restore_noise($name); // might be a noisy name
|
1853 |
+
if ($this->lowercase) $name = strtolower($name);
|
1854 |
+
if ($this->char==='=') { // attribute with value
|
1855 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1856 |
+
$this->parse_attr($node, $name, $space); // get attribute value
|
1857 |
+
}
|
1858 |
+
else {
|
1859 |
+
//no value attr: nowrap, checked selected...
|
1860 |
+
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
|
1861 |
+
$node->attr[$name] = true;
|
1862 |
+
if ($this->char!='>') $this->char = $this->doc[--$this->pos]; // prev
|
1863 |
+
}
|
1864 |
+
$node->_[HDOM_INFO_SPACE][] = $space;
|
1865 |
+
$space = array($this->copy_skip($this->token_blank), '', ''); // prepare for next attribute
|
1866 |
+
}
|
1867 |
+
else // no more attributes
|
1868 |
+
break;
|
1869 |
+
} while ($this->char!=='>' && $this->char!=='/'); // go until the tag ended
|
1870 |
+
|
1871 |
+
$this->link_nodes($node, true);
|
1872 |
+
$node->_[HDOM_INFO_ENDSPACE] = $space[0];
|
1873 |
+
|
1874 |
+
// handle empty tags (i.e. "<div/>")
|
1875 |
+
if ($this->copy_until_char('>')==='/')
|
1876 |
+
{
|
1877 |
+
$node->_[HDOM_INFO_ENDSPACE] .= '/';
|
1878 |
+
$node->_[HDOM_INFO_END] = 0;
|
1879 |
+
}
|
1880 |
+
else
|
1881 |
+
{
|
1882 |
+
// reset parent
|
1883 |
+
if (!isset($this->self_closing_tags[strtolower($node->tag)])) $this->parent = $node;
|
1884 |
+
}
|
1885 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1886 |
+
|
1887 |
+
// If it's a BR tag, we need to set it's text to the default text.
|
1888 |
+
// This way when we see it in plaintext, we can generate formatting that the user wants.
|
1889 |
+
// since a br tag never has sub nodes, this works well.
|
1890 |
+
if ($node->tag == "br")
|
1891 |
+
{
|
1892 |
+
$node->_[HDOM_INFO_INNER] = $this->default_br_text;
|
1893 |
+
}
|
1894 |
+
|
1895 |
+
return true;
|
1896 |
+
}
|
1897 |
+
|
1898 |
+
/**
|
1899 |
+
* Parse attribute from current document position
|
1900 |
+
*
|
1901 |
+
* @param object $node Node for the attributes
|
1902 |
+
* @param string $name Name of the current attribute
|
1903 |
+
* @param array $space Array for spacing information
|
1904 |
+
* @return void
|
1905 |
+
*/
|
1906 |
+
protected function parse_attr($node, $name, &$space)
|
1907 |
+
{
|
1908 |
+
// Per sourceforge: http://sourceforge.net/tracker/?func=detail&aid=3061408&group_id=218559&atid=1044037
|
1909 |
+
// If the attribute is already defined inside a tag, only pay attention to the first one as opposed to the last one.
|
1910 |
+
// https://stackoverflow.com/a/26341866
|
1911 |
+
if (isset($node->attr[$name]))
|
1912 |
+
{
|
1913 |
+
return;
|
1914 |
+
}
|
1915 |
+
|
1916 |
+
$space[2] = $this->copy_skip($this->token_blank); // [2] Whitespace between "=" and the value
|
1917 |
+
switch ($this->char) {
|
1918 |
+
case '"': // value is anything between double quotes
|
1919 |
+
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE;
|
1920 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1921 |
+
$node->attr[$name] = $this->restore_noise($this->copy_until_char('"'));
|
1922 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1923 |
+
break;
|
1924 |
+
case '\'': // value is anything between single quotes
|
1925 |
+
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_SINGLE;
|
1926 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1927 |
+
$node->attr[$name] = $this->restore_noise($this->copy_until_char('\''));
|
1928 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1929 |
+
break;
|
1930 |
+
default: // value is anything until the first space or end tag
|
1931 |
+
$node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO;
|
1932 |
+
$node->attr[$name] = $this->restore_noise($this->copy_until($this->token_attr));
|
1933 |
+
}
|
1934 |
+
// PaperG: Attributes should not have \r or \n in them, that counts as html whitespace.
|
1935 |
+
$node->attr[$name] = str_replace("\r", "", $node->attr[$name]);
|
1936 |
+
$node->attr[$name] = str_replace("\n", "", $node->attr[$name]);
|
1937 |
+
// PaperG: If this is a "class" selector, lets get rid of the preceeding and trailing space since some people leave it in the multi class case.
|
1938 |
+
if ($name == "class") {
|
1939 |
+
$node->attr[$name] = trim($node->attr[$name]);
|
1940 |
+
}
|
1941 |
+
}
|
1942 |
+
|
1943 |
+
/**
|
1944 |
+
* Link node to parent node
|
1945 |
+
*
|
1946 |
+
* @param object $node Node to link to parent
|
1947 |
+
* @param bool $is_child True if the node is a child of parent
|
1948 |
+
* @return void
|
1949 |
+
*/
|
1950 |
+
// link node's parent
|
1951 |
+
protected function link_nodes(&$node, $is_child)
|
1952 |
+
{
|
1953 |
+
$node->parent = $this->parent;
|
1954 |
+
$this->parent->nodes[] = $node;
|
1955 |
+
if ($is_child)
|
1956 |
+
{
|
1957 |
+
$this->parent->children[] = $node;
|
1958 |
+
}
|
1959 |
+
}
|
1960 |
+
|
1961 |
+
/**
|
1962 |
+
* Add tag as text node to current node
|
1963 |
+
*
|
1964 |
+
* @param string $tag Tag name
|
1965 |
+
* @return bool True on success
|
1966 |
+
*/
|
1967 |
+
protected function as_text_node($tag)
|
1968 |
+
{
|
1969 |
+
$node = new simple_html_dom_node($this);
|
1970 |
+
++$this->cursor;
|
1971 |
+
$node->_[HDOM_INFO_TEXT] = '</' . $tag . '>';
|
1972 |
+
$this->link_nodes($node, false);
|
1973 |
+
$this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1974 |
+
return true;
|
1975 |
+
}
|
1976 |
+
|
1977 |
+
/**
|
1978 |
+
* Seek from the current document position to the first occurrence of a
|
1979 |
+
* character not defined by the provided string. Update the current document
|
1980 |
+
* position to the new position.
|
1981 |
+
*
|
1982 |
+
* @param string $chars A string containing every allowed character.
|
1983 |
+
* @return void
|
1984 |
+
*/
|
1985 |
+
protected function skip($chars)
|
1986 |
+
{
|
1987 |
+
$this->pos += strspn($this->doc, $chars, $this->pos);
|
1988 |
+
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
1989 |
+
}
|
1990 |
+
|
1991 |
+
/**
|
1992 |
+
* Copy substring from the current document position to the first occurrence
|
1993 |
+
* of a character not defined by the provided string.
|
1994 |
+
*
|
1995 |
+
* @param string $chars A string containing every allowed character.
|
1996 |
+
* @return string Substring from the current document position to the first
|
1997 |
+
* occurrence of a character not defined by the provided string.
|
1998 |
+
*/
|
1999 |
+
protected function copy_skip($chars)
|
2000 |
+
{
|
2001 |
+
$pos = $this->pos;
|
2002 |
+
$len = strspn($this->doc, $chars, $pos);
|
2003 |
+
$this->pos += $len;
|
2004 |
+
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
2005 |
+
if ($len===0) return '';
|
2006 |
+
return substr($this->doc, $pos, $len);
|
2007 |
+
}
|
2008 |
+
|
2009 |
+
/**
|
2010 |
+
* Copy substring from the current document position to the first occurrence
|
2011 |
+
* of any of the provided characters.
|
2012 |
+
*
|
2013 |
+
* @param string $chars A string containing every character to stop at.
|
2014 |
+
* @return string Substring from the current document position to the first
|
2015 |
+
* occurrence of any of the provided characters.
|
2016 |
+
*/
|
2017 |
+
protected function copy_until($chars)
|
2018 |
+
{
|
2019 |
+
$pos = $this->pos;
|
2020 |
+
$len = strcspn($this->doc, $chars, $pos);
|
2021 |
+
$this->pos += $len;
|
2022 |
+
$this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next
|
2023 |
+
return substr($this->doc, $pos, $len);
|
2024 |
+
}
|
2025 |
+
|
2026 |
+
/**
|
2027 |
+
* Copy substring from the current document position to the first occurrence
|
2028 |
+
* of the provided string.
|
2029 |
+
*
|
2030 |
+
* @param string $char The string to stop at.
|
2031 |
+
* @return string Substring from the current document position to the first
|
2032 |
+
* occurrence of the provided string.
|
2033 |
+
*/
|
2034 |
+
protected function copy_until_char($char)
|
2035 |
+
{
|
2036 |
+
if ($this->char===null) return '';
|
2037 |
+
|
2038 |
+
if (($pos = strpos($this->doc, $char, $this->pos))===false) {
|
2039 |
+
$ret = substr($this->doc, $this->pos, $this->size-$this->pos);
|
2040 |
+
$this->char = null;
|
2041 |
+
$this->pos = $this->size;
|
2042 |
+
return $ret;
|
2043 |
+
}
|
2044 |
+
|
2045 |
+
if ($pos===$this->pos) return '';
|
2046 |
+
$pos_old = $this->pos;
|
2047 |
+
$this->char = $this->doc[$pos];
|
2048 |
+
$this->pos = $pos;
|
2049 |
+
return substr($this->doc, $pos_old, $pos-$pos_old);
|
2050 |
+
}
|
2051 |
+
|
2052 |
+
/**
|
2053 |
+
* Remove noise from HTML content
|
2054 |
+
*
|
2055 |
+
* Noise is stored to {@see simple_html_dom::$noise}
|
2056 |
+
*
|
2057 |
+
* @param string $pattern The regex pattern used for finding noise
|
2058 |
+
* @param bool $remove_tag True to remove the entire match. Default is false
|
2059 |
+
* to only remove the captured data.
|
2060 |
+
*/
|
2061 |
+
protected function remove_noise($pattern, $remove_tag=false)
|
2062 |
+
{
|
2063 |
+
global $debug_object;
|
2064 |
+
if (is_object($debug_object)) { $debug_object->debug_log_entry(1); }
|
2065 |
+
|
2066 |
+
$count = preg_match_all($pattern, $this->doc, $matches, PREG_SET_ORDER|PREG_OFFSET_CAPTURE);
|
2067 |
+
|
2068 |
+
for ($i=$count-1; $i>-1; --$i)
|
2069 |
+
{
|
2070 |
+
$key = '___noise___'.sprintf('% 5d', count($this->noise)+1000);
|
2071 |
+
if (is_object($debug_object)) { $debug_object->debug_log(2, 'key is: ' . $key); }
|
2072 |
+
$idx = ($remove_tag) ? 0 : 1; // 0 = entire match, 1 = submatch
|
2073 |
+
$this->noise[$key] = $matches[$i][$idx][0];
|
2074 |
+
$this->doc = substr_replace($this->doc, $key, $matches[$i][$idx][1], strlen($matches[$i][$idx][0]));
|
2075 |
+
}
|
2076 |
+
|
2077 |
+
// reset the length of content
|
2078 |
+
$this->size = strlen($this->doc);
|
2079 |
+
if ($this->size>0)
|
2080 |
+
{
|
2081 |
+
$this->char = $this->doc[0];
|
2082 |
+
}
|
2083 |
+
}
|
2084 |
+
|
2085 |
+
/**
|
2086 |
+
* Restore noise to HTML content
|
2087 |
+
*
|
2088 |
+
* Noise is restored from {@see simple_html_dom::$noise}
|
2089 |
+
*
|
2090 |
+
* @param string $text A subset of HTML containing noise
|
2091 |
+
* @return string The same content with noise restored
|
2092 |
+
*/
|
2093 |
+
function restore_noise($text)
|
2094 |
+
{
|
2095 |
+
global $debug_object;
|
2096 |
+
if (is_object($debug_object)) { $debug_object->debug_log_entry(1); }
|
2097 |
+
|
2098 |
+
while (($pos=strpos($text, '___noise___'))!==false)
|
2099 |
+
{
|
2100 |
+
// Sometimes there is a broken piece of markup, and we don't GET the pos+11 etc... token which indicates a problem outside of us...
|
2101 |
+
if (strlen($text) > $pos+15)
|
2102 |
+
{ // todo: "___noise___1000" (or any number with four or more digits) in the DOM causes an infinite loop which could be utilized by malicious software
|
2103 |
+
$key = '___noise___'.$text[$pos+11].$text[$pos+12].$text[$pos+13].$text[$pos+14].$text[$pos+15];
|
2104 |
+
if (is_object($debug_object)) { $debug_object->debug_log(2, 'located key of: ' . $key); }
|
2105 |
+
|
2106 |
+
if (isset($this->noise[$key]))
|
2107 |
+
{
|
2108 |
+
$text = substr($text, 0, $pos).$this->noise[$key].substr($text, $pos+16);
|
2109 |
+
}
|
2110 |
+
else
|
2111 |
+
{
|
2112 |
+
// do this to prevent an infinite loop.
|
2113 |
+
$text = substr($text, 0, $pos).'UNDEFINED NOISE FOR KEY: '.$key . substr($text, $pos+16);
|
2114 |
+
}
|
2115 |
+
}
|
2116 |
+
else
|
2117 |
+
{
|
2118 |
+
// There is no valid key being given back to us... We must get rid of the ___noise___ or we will have a problem.
|
2119 |
+
$text = substr($text, 0, $pos).'NO NUMERIC NOISE KEY' . substr($text, $pos+11);
|
2120 |
+
}
|
2121 |
+
}
|
2122 |
+
return $text;
|
2123 |
+
}
|
2124 |
+
|
2125 |
+
// Sometimes we NEED one of the noise elements.
|
2126 |
+
function search_noise($text)
|
2127 |
+
{
|
2128 |
+
global $debug_object;
|
2129 |
+
if (is_object($debug_object)) { $debug_object->debug_log_entry(1); }
|
2130 |
+
|
2131 |
+
foreach($this->noise as $noiseElement)
|
2132 |
+
{
|
2133 |
+
if (strpos($noiseElement, $text)!==false)
|
2134 |
+
{
|
2135 |
+
return $noiseElement;
|
2136 |
+
}
|
2137 |
+
}
|
2138 |
+
}
|
2139 |
+
function __toString()
|
2140 |
+
{
|
2141 |
+
return $this->root->innertext();
|
2142 |
+
}
|
2143 |
+
|
2144 |
+
function __get($name)
|
2145 |
+
{
|
2146 |
+
switch ($name)
|
2147 |
+
{
|
2148 |
+
case 'outertext':
|
2149 |
+
return $this->root->innertext();
|
2150 |
+
case 'innertext':
|
2151 |
+
return $this->root->innertext();
|
2152 |
+
case 'plaintext':
|
2153 |
+
return $this->root->text();
|
2154 |
+
case 'charset':
|
2155 |
+
return $this->_charset;
|
2156 |
+
case 'target_charset':
|
2157 |
+
return $this->_target_charset;
|
2158 |
+
}
|
2159 |
+
}
|
2160 |
+
|
2161 |
+
// camel naming conventions
|
2162 |
+
function childNodes($idx=-1) {return $this->root->childNodes($idx);}
|
2163 |
+
function firstChild() {return $this->root->first_child();}
|
2164 |
+
function lastChild() {return $this->root->last_child();}
|
2165 |
+
function createElement($name, $value=null) {return @str_get_html("<$name>$value</$name>")->first_child();}
|
2166 |
+
function createTextNode($value) {return @end(str_get_html($value)->nodes);}
|
2167 |
+
function getElementById($id) {return $this->find("#$id", 0);}
|
2168 |
+
function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);}
|
2169 |
+
function getElementByTagName($name) {return $this->find($name, 0);}
|
2170 |
+
function getElementsByTagName($name, $idx=-1) {return $this->find($name, $idx);}
|
2171 |
+
function loadFile() {$args = func_get_args();$this->load_file($args);}
|
2172 |
+
}
|
2173 |
+
|
2174 |
+
?>
|